© 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. 32-TRANSCODER-HP
    7. 42068
    Prev
    Next
    INDEX
    Explanations

    Pro

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vir
    -0.35
     Ve
    -0.30
    ve
    -0.28
     ve
    -0.27
    iked
    -0.26
    èĢĺ
    -0.26
    iterr
    -0.26
    ardy
    -0.26
     vig
    -0.25
    å¹´ä¹ĭä¹ħ
    -0.25
    POSITIVE LOGITS
    nb
    0.28
    erset
    0.28
    hibition
    0.26
    è½´
    0.26
    ATURE
    0.26
    Pawn
    0.26
    æĥij
    0.25
    ;set
    0.25
    alion
    0.25
    ç»Ģ
    0.25
    Activations Density 0.001%

    No Known Activations