© 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. 20-TRANSCODER-HP
    7. 130691
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ])->
    -0.29
    å¾Īéĩįè¦ģçļĦ
    -0.26
     peru
    -0.25
    abel
    -0.24
    abble
    -0.24
    _aa
    -0.24
    inel
    -0.24
    dorf
    -0.24
    inea
    -0.23
    master
    -0.23
    POSITIVE LOGITS
    .FileInputStream
    0.25
    æ½®
    0.25
    -bootstrap
    0.24
     Coast
    0.24
    æ¶İ
    0.24
    åīįä¸ĸ
    0.24
    enti
    0.23
    èĻļåģĩ
    0.23
    æĬ¤
    0.23
    詹å§Ĩ
    0.23
    Activations Density 16.597%

    No Known Activations

    This feature has no known activations.