© 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
    2. Qwen3-4B
    3. 32-TRANSCODER-HP
    4. 42417
    Prev
    Next
    INDEX
    Explanations

    of

    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
     Uncomment
    -0.25
    åºķå±Ĥ
    -0.25
    .tf
    -0.24
    ä¸Ĭä¸ĭ游
    -0.24
     causal
    -0.24
    acional
    -0.23
    .matches
    -0.23
    çΰ
    -0.23
    ****↵
    -0.23
     Sellers
    -0.23
    POSITIVE LOGITS
    ugins
    0.29
     things
    0.27
     orth
    0.27
     emb
    0.26
     wearing
    0.26
    请æĤ¨
    0.26
    pher
    0.25
    things
    0.25
    alty
    0.25
    ients
    0.25
    Activations Density 0.002%

    No Known Activations