© 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. 12-TRANSCODER-HP
    7. 23084
    Prev
    Next
    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erged
    -0.32
    utm
    -0.27
    _intensity
    -0.26
     COMMAND
    -0.24
    èĬĻèĵī
    -0.24
    edere
    -0.24
    éħ¿éĢł
    -0.24
    误差
    -0.24
    æĸ°å¼Ģ
    -0.24
    æķħæĦı
    -0.23
    POSITIVE LOGITS
    æĸ¹å¼ıè¿Ľè¡Į
    0.30
    æľīæķĪæĢ§
    0.29
    jr
    0.27
    vals
    0.26
    ally
    0.26
    aar
    0.25
    ARN
    0.25
    icers
    0.25
    JR
    0.25
    segment
    0.25
    Activations Density 0.000%

    No Known Activations