© 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. 40623
    Prev
    Next
    INDEX
    Explanations

    School

    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
    ched
    -0.36
    ä¸įå®ļ
    -0.31
     preval
    -0.27
    FRING
    -0.25
     schedules
    -0.25
     abbrev
    -0.25
     shorten
    -0.25
    åĪ¶åº¦
    -0.24
    å¾Ļ
    -0.24
     substitutes
    -0.24
    POSITIVE LOGITS
    alse
    0.31
    orado
    0.28
    arten
    0.27
     Sour
    0.26
    еÑģÑģ
    0.26
     SOUR
    0.26
    odesk
    0.25
    perse
    0.25
    éĶŃ
    0.24
    åĴĮæĬĢæľ¯
    0.24
    Activations Density 0.982%

    No Known Activations