© 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. 142228
    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
    ä½ľçĶ¨
    -0.26
    ı
    -0.25
     discipl
    -0.25
     g
    -0.25
    è¾ĺ
    -0.25
     stabil
    -0.24
    elle
    -0.24
    :selected
    -0.24
    {{--
    -0.24
    ib
    -0.24
    POSITIVE LOGITS
    马ä¸Ĭå°±
    0.27
    马ä¸Ĭ
    0.26
    tings
    0.26
    setter
    0.25
    常说
    0.25
    panse
    0.25
    _Move
    0.24
    sing
    0.24
    ç§ĭ
    0.24
     movable
    0.24
    Activations Density 2.993%

    No Known Activations

    This feature has no known activations.