© 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. 9-TRANSCODER-HP
    7. 29773
    Prev
    Next
    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¯ī
    -0.28
    specifier
    -0.28
    æľ¬æ¡Ī
    -0.27
    ä¹ł
    -0.26
    -DD
    -0.25
     originals
    -0.25
    Scripts
    -0.25
    çIJ¥
    -0.25
    alia
    -0.24
    æģ°
    -0.24
    POSITIVE LOGITS
     grades
    0.26
    ãĥļ
    0.26
    ForResource
    0.26
    ä¸įä¸ĭ
    0.25
    ainless
    0.25
    è¯Ĩ
    0.25
    uese
    0.25
    eous
    0.25
     Peters
    0.24
    #endregion
    0.24
    Activations Density 1.215%

    No Known Activations