© 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. 24-TRANSCODER-HP
    7. 149683
    Prev
    Next
    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    让åѦçĶŁ
    -0.27
    ç¬ij容
    -0.26
    票
    -0.26
    fix
    -0.25
    ä¸ĢæŃ¥
    -0.24
     qed
    -0.24
    款
    -0.24
    ê¸Ī
    -0.23
    æĿĢèıĮ
    -0.23
    éĿ¢åŃĶ
    -0.23
    POSITIVE LOGITS
    认为
    0.32
    aker
    0.30
     envision
    0.28
    ertest
    0.26
    okers
    0.25
     Miner
    0.25
    ureau
    0.25
    ois
    0.25
    _LITERAL
    0.24
    AKER
    0.24
    Activations Density 0.127%

    No Known Activations