© 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. 14-TRANSCODER-HP
    7. 40030
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    *X
    -0.26
    EntityManager
    -0.26
    æ°¸
    -0.26
    åįģéĩĮ
    -0.25
     dia
    -0.25
     McLaren
    -0.25
    æ°¸æģĴ
    -0.25
    óg
    -0.25
     X
    -0.23
    åŃ
    -0.23
    POSITIVE LOGITS
    ingly
    0.28
    çķı
    0.26
    drawing
    0.26
     mee
    0.26
     Explosion
    0.25
    ationToken
    0.25
    alias
    0.24
    advisor
    0.24
    -counter
    0.24
     ///<
    0.23
    Activations Density 0.088%

    No Known Activations