© 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. 43015
    Prev
    Next
    INDEX
    Explanations

    News stations

    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
     paren
    -0.31
    æ°´éĿ¢
    -0.28
    æĭ¾
    -0.28
     sol
    -0.26
    che
    -0.26
    itters
    -0.25
    ite
    -0.25
    íĴĢ
    -0.24
    oko
    -0.24
    ivirus
    -0.24
    POSITIVE LOGITS
    arde
    0.28
     nu
    0.27
    aroo
    0.26
    .ax
    0.26
    Nu
    0.24
    饶
    0.24
     вкÑĥÑģ
    0.24
    èķĻ
    0.24
    KHR
    0.24
    ipa
    0.23
    Activations Density 0.003%

    No Known Activations