© 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. 9503
    Prev
    Next
    INDEX
    Explanations

    New Zealand

    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
    交
    -0.32
    转åħ¥
    -0.30
    pine
    -0.29
    ao
    -0.29
    æĴķ
    -0.28
    ç§ij
    -0.28
    oh
    -0.28
     obl
    -0.27
    æĶ¶
    -0.27
    交åıī
    -0.27
    POSITIVE LOGITS
     favoured
    0.31
     Whilst
    0.27
     recognise
    0.27
    ç®ĹäºĨ
    0.26
     sector
    0.26
     HttpRequest
    0.25
    REQ
    0.25
    æĸ¼æĺ¯
    0.25
    ãģªãģĦãģ§ãģĻ
    0.25
    Whilst
    0.24
    Activations Density 0.032%

    No Known Activations