© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 39760
    Prev
    Next
    INDEX
    Explanations

    reporting

    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
    åı¯æĢķ
    -0.27
    ä¿Ŀå¯Ĩ
    -0.27
    èĻij
    -0.26
     insanely
    -0.26
    æĹĭ
    -0.25
    ç»Ļä½łä»¬
    -0.25
    缸äºĴ
    -0.24
    丰ç¡ķ
    -0.24
    æľŁæľĽ
    -0.24
    缸çĪ±
    -0.23
    POSITIVE LOGITS
    çĿ¹
    0.32
    ä¸ī人
    0.29
    ató
    0.27
    vidia
    0.25
    读åIJİ
    0.25
    styled
    0.25
    ä¸īä½įä¸Ģä½ĵ
    0.24
     Fibonacci
    0.24
     trio
    0.24
     пÑĢоиÑģ
    0.23
    Activations Density 0.125%

    No Known Activations