© 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. 19475
    Prev
    Next
    INDEX
    Explanations

    {

    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
    asking
    -0.29
    Asked
    -0.27
    DMIN
    -0.27
     cancell
    -0.25
    antha
    -0.25
     Wheels
    -0.25
     Canc
    -0.25
    æĸ°ä¸ĸ纪
    -0.25
    çĤ¸
    -0.24
    etroit
    -0.24
    POSITIVE LOGITS
    -Regular
    0.28
    [right
    0.26
     pal
    0.25
    第äºĮ天
    0.25
    å±±åİ¿
    0.25
    charger
    0.24
    ç¾İåij³
    0.23
    ipt
    0.23
    åį«æĺŁ
    0.23
    ode
    0.23
    Activations Density 0.835%

    No Known Activations