© 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. 25-TRANSCODER-HP
    7. 108751
    Prev
    Next
    INDEX
    Explanations

    Academic/formal writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    witch
    -0.26
    ä¿¡æģ¯æľįåĬ¡
    -0.26
     straw
    -0.26
    çī¹æ´¾åijĺ
    -0.26
    ativa
    -0.25
    åĴ¤
    -0.24
    åŀĭä¼ģä¸ļ
    -0.24
    inux
    -0.24
    iny
    -0.24
    æ´»æĢ§
    -0.24
    POSITIVE LOGITS
    ToFit
    0.31
    æĬķ
    0.25
    ç»ıå¼Ģ
    0.24
    以人为
    0.24
    \Unit
    0.24
     Wiring
    0.23
    il
    0.23
     uncomment
    0.23
    å§Ķ
    0.23
    _TS
    0.22
    Activations Density 0.916%

    No Known Activations