© 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. 98607
    Prev
    Next
    INDEX
    Explanations

    Document metadata and code

    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
    缴åĪ°
    -0.30
    road
    -0.26
     stretch
    -0.26
     uninterrupted
    -0.26
    åľ¨åħ¨çIJĥ
    -0.25
    raid
    -0.25
     until
    -0.25
     fractions
    -0.24
    ix
    -0.24
    çĶŁæ´»ä¸Ń
    -0.24
    POSITIVE LOGITS
    htag
    0.30
     lle
    0.30
    gle
    0.25
    åħ³éĶ®æĬĢæľ¯
    0.25
    ìĬ¨
    0.24
    大家åı¯ä»¥
    0.24
    obre
    0.24
    sville
    0.24
    uben
    0.24
    entine
    0.23
    Activations Density 0.016%

    No Known Activations