© 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. 27-TRANSCODER-HP
    7. 56991
    Prev
    Next
    INDEX
    Explanations

    non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    modification
    -0.27
    lobs
    -0.27
    lots
    -0.27
     happiest
    -0.26
    -packages
    -0.26
     rejo
    -0.25
    (kv
    -0.25
    ãģĭãģijãģ¦
    -0.25
    å¸ĥ
    -0.25
    å¯Įè´µ
    -0.25
    POSITIVE LOGITS
    ä¸įåIJĪçIJĨ
    0.30
    ä¸įç¡®å®ļ
    0.28
     ine
    0.27
    æŀª
    0.27
    礼
    0.26
    åĻªå£°
    0.26
    åĻªéŁ³
    0.26
     Une
    0.26
    为ä»Ģä¹Īä¸į
    0.26
    (Log
    0.25
    Activations Density 0.003%

    No Known Activations