© 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. 39150
    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
     fc
    -0.26
    pj
    -0.26
    audi
    -0.25
    cycl
    -0.25
    (mx
    -0.25
    çłµ
    -0.25
     Anaheim
    -0.24
    msgs
    -0.24
     stoi
    -0.24
     Peb
    -0.24
    POSITIVE LOGITS
    æĮ¯ãĤĬ
    0.24
    çºłæŃ£
    0.24
    æīįåı¯ä»¥
    0.24
    ulu
    0.23
    èľĺèĽĽ
    0.23
    æ¯Ķéĩį
    0.23
    Correct
    0.23
    伺
    0.23
    /service
    0.23
    溯
    0.23
    Activations Density 30.033%

    No Known Activations

    This feature has no known activations.