© 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. 97982
    Prev
    Next
    INDEX
    Explanations

    descriptions and relationships

    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
    relations
    -0.25
    olla
    -0.25
     Educação
    -0.25
    'article
    -0.25
     Overs
    -0.24
    åħ³ç³»
    -0.24
    åĽ½æľī
    -0.24
    encias
    -0.24
    彩èī²
    -0.24
    oftware
    -0.23
    POSITIVE LOGITS
     ips
    0.25
     unfolding
    0.24
    sla
    0.24
     unsub
    0.24
    делÑĮ
    0.24
    etto
    0.24
    epad
    0.24
     unf
    0.24
     all
    0.24
    gee
    0.24
    Activations Density 0.003%

    No Known Activations