© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39443
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<↵
    -0.28
    ä»»ä½ķ人
    -0.26
     corruption
    -0.26
     quo
    -0.26
     Corruption
    -0.26
    åĽ½å®¶å®īåħ¨
    -0.25
    ä»ĸå¦Ī
    -0.25
    类似çļĦ
    -0.25
     ******************************************************************************/↵↵
    -0.24
    ÅĽl
    -0.24
    POSITIVE LOGITS
    mans
    0.26
    _SF
    0.25
    顺
    0.24
    (rank
    0.24
    lander
    0.24
    ÑģеÑĢ
    0.24
    erv
    0.23
    hill
    0.23
    .Fore
    0.23
    åģ¶
    0.23
    Activations Density 58.845%

    No Known Activations

    This feature has no known activations.