© 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. 18716
    Prev
    Next
    INDEX
    Explanations

    technical and formal language

    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
    leine
    -0.30
    ugins
    -0.28
    cept
    -0.27
     gag
    -0.27
    大家åĪĨ享
    -0.26
    ragon
    -0.26
    åĶ¯
    -0.26
    lrt
    -0.25
    heiten
    -0.25
    èµŁ
    -0.25
    POSITIVE LOGITS
     commod
    0.29
    APO
    0.27
    sap
    0.27
    士
    0.25
     volont
    0.25
    人士
    0.25
    æ³µ
    0.24
    ç£ħ
    0.23
    dbc
    0.23
     Prote
    0.23
    Activations Density 0.114%

    No Known Activations