© 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. 39924
    Prev
    Next
    INDEX
    Explanations

    Formal/technical writing

    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
    主人åħ¬
    -0.26
     METH
    -0.26
    åŁ
    -0.26
     Monad
    -0.25
    çĶ·ä¸»è§Ĵ
    -0.25
    女主è§Ĵ
    -0.25
    ç¼ł
    -0.24
    .defaultProps
    -0.24
     \"$
    -0.23
    è¿ĶåĽŀæIJľçĭIJ
    -0.23
    POSITIVE LOGITS
    oft
    0.31
     cust
    0.29
    åĿļå®Ī
    0.26
     notes
    0.25
    å·¥ä¸ļä¼ģä¸ļ
    0.25
     central
    0.24
    <>↵
    0.23
    .pb
    0.23
     Pl
    0.23
    ger
    0.23
    Activations Density 0.135%

    No Known Activations