© 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. 22-TRANSCODER-HP
    7. 88467
    Prev
    Next
    INDEX
    Explanations

    Internet posts and legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĢı
    -0.32
    åĿ³
    -0.28
    éģ¿
    -0.28
    æĶ¶æķĽ
    -0.27
     transparency
    -0.26
     guarantees
    -0.26
    转è¿IJ
    -0.26
    åĢĴå¡Į
    -0.26
     guarantee
    -0.26
    quette
    -0.25
    POSITIVE LOGITS
    èµ·è¯ī
    0.36
    追
    0.31
    éĺ²çĽĹ
    0.30
    ç»´æĿĥ
    0.30
    æݧ
    0.29
    ä¿ĿæĬ¤
    0.28
     thief
    0.28
     chase
    0.27
     escorts
    0.27
     protect
    0.27
    Activations Density 0.012%

    No Known Activations