© 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. 141137
    Prev
    Next
    INDEX
    Explanations

    code and technical writing

    np_max-act · gemini-2.0-flash
    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
    æ¯Ĵ
    -0.32
     co
    -0.30
    rosse
    -0.29
    åī©ä½Ļ
    -0.26
    åĪĨæĶ¯
    -0.26
     remaining
    -0.26
    ocument
    -0.25
    éĥ¨åĪĨ
    -0.25
    éĥ¨
    -0.25
     resto
    -0.25
    POSITIVE LOGITS
    prefs
    0.31
     lòng
    0.26
    ertools
    0.26
     vending
    0.25
    _pref
    0.25
    изм
    0.25
    åĤĢ
    0.25
     Pref
    0.24
    _prefs
    0.24
    åİŁä¾Ĩ
    0.24
    Activations Density 44.892%

    No Known Activations