© 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. 33-TRANSCODER-HP
    7. 53410
    Prev
    Next
    INDEX
    Explanations

    say 0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.28
     seventeen
    -0.27
    çŁ¥éģĵèĩªå·±
    -0.26
    undred
    -0.26
    strument
    -0.24
    åŀĥåľ¾æ¡¶
    -0.24
    _INITIALIZ
    -0.24
     twelve
    -0.24
    $action
    -0.24
     {}:
    -0.24
    POSITIVE LOGITS
    ild
    0.29
     Gim
    0.28
    esters
    0.28
    zet
    0.27
    fdc
    0.27
    leo
    0.27
    ONY
    0.26
    è¡¿
    0.26
    angel
    0.25
    clare
    0.25
    Activations Density 0.088%

    No Known Activations