© 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. 39825
    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
     ÑģоÑħÑĢ
    -0.27
     coastal
    -0.27
    æķ´é¡¿
    -0.26
    ioned
    -0.25
    âĩ¨
    -0.24
    åIJĮå¿Ĺ
    -0.24
    spender
    -0.24
     retros
    -0.24
     dies
    -0.24
     Mojo
    -0.23
    POSITIVE LOGITS
    agens
    0.29
    ugal
    0.27
    isci
    0.27
    ĭè¯ķ
    0.27
    AME
    0.26
    ales
    0.26
    ITCH
    0.25
    çĬ¯
    0.25
    ALLE
    0.25
    Ñĥй
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.