© 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. 150018
    Prev
    Next
    INDEX
    Explanations

    take

    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
    /material
    -0.30
     Material
    -0.26
     material
    -0.26
    æĿIJ
    -0.25
    åĪĽä¸ļèĢħ
    -0.25
    IBUTE
    -0.25
    imbus
    -0.25
    иÑĢовка
    -0.24
    ä¸ĢèĤ¡
    -0.24
    |min
    -0.23
    POSITIVE LOGITS
    ToOne
    0.28
    篷
    0.28
    _settings
    0.26
    éĿ¢å¯¹éĿ¢
    0.26
     targets
    0.25
     tá»Ń
    0.25
    ¡°
    0.25
    UV
    0.25
    acad
    0.24
    Father
    0.24
    Activations Density 0.058%

    No Known Activations