© 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. 19-TRANSCODER-HP
    7. 7749
    Prev
    Next
    INDEX
    Explanations

    firstname

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    课
    -0.25
    è®Ń
    -0.25
    使èĢħ
    -0.24
    iples
    -0.24
    UIS
    -0.23
    preh
    -0.23
    åĮ»ç§ij大åѦ
    -0.23
    è¿ĩ大
    -0.23
    \"]
    -0.23
     uncon
    -0.23
    POSITIVE LOGITS
    emente
    0.26
     hourly
    0.25
    toa
    0.25
    çŃ
    0.24
     pitched
    0.24
    ØŃسب
    0.24
    à¹Ģà¸ľ
    0.24
    arah
    0.24
    achs
    0.23
    fahren
    0.23
    Activations Density 0.016%

    No Known Activations