© 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. 14-TRANSCODER-HP
    7. 40415
    Prev
    Next
    INDEX
    Explanations

    Displayed, visible, activated

    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
     anonymous
    -0.30
     randomly
    -0.28
    god
    -0.27
     Score
    -0.26
     diz
    -0.25
    vip
    -0.25
    anonymous
    -0.25
    æ¤İ
    -0.25
     copy
    -0.25
    Sc
    -0.24
    POSITIVE LOGITS
    èĭ¦èĭ¦
    0.28
    orny
    0.27
    füh
    0.25
    CGRect
    0.25
     triggering
    0.25
    èĢĮæĿ¥
    0.24
    ä¸ĢæŶ
    0.24
     Dead
    0.24
    rica
    0.24
    MouseMove
    0.24
    Activations Density 0.100%

    No Known Activations