© 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. 31-TRANSCODER-HP
    7. 18524
    Prev
    Next
    INDEX
    Explanations

    Kaw

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flats
    -0.31
    æĬĺåıł
    -0.28
     flat
    -0.28
     gab
    -0.28
    æŃ¥
    -0.25
    lev
    -0.25
     disp
    -0.25
    _RPC
    -0.24
     Bord
    -0.24
     Flat
    -0.24
    POSITIVE LOGITS
    .begin
    0.29
    teenth
    0.27
    .go
    0.26
    说å®ŀ
    0.25
    rente
    0.25
    èģŀãģı
    0.25
    волÑĮ
    0.24
    çĸļ
    0.24
    entr
    0.24
    lte
    0.24
    Activations Density 0.005%

    No Known Activations