© 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. 18622
    Prev
    Next
    INDEX
    Explanations

    bin

    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
    gos
    -0.33
    jac
    -0.29
     gy
    -0.26
    neh
    -0.26
     refl
    -0.26
    æѸ
    -0.25
    icot
    -0.25
    ä¼łç»Łäº§ä¸ļ
    -0.25
     Vib
    -0.25
    ary
    -0.25
    POSITIVE LOGITS
    structor
    0.25
    ewater
    0.25
    osen
    0.25
    ears
    0.24
    Triple
    0.24
    æĻĴ
    0.24
    å¹²
    0.24
    æĺĨæĺİ
    0.24
    åŃIJ
    0.24
    onto
    0.23
    Activations Density 0.003%

    No Known Activations