© 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. 98081
    Prev
    Next
    INDEX
    Explanations

    Comma

    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
    èĪ¬
    -0.27
    artz
    -0.26
    odon
    -0.26
     pyramid
    -0.26
    æ²»çIJĨä½ĵç³»
    -0.26
     /**<
    -0.25
     off
    -0.24
    à¸Ľà¸£à¸²
    -0.24
    fol
    -0.24
    hari
    -0.24
    POSITIVE LOGITS
    è·£
    0.25
    ä¹Łæĺ¯å¾Ī
    0.25
     Latter
    0.24
     facult
    0.24
    æĺ¯æľī
    0.24
    åĨįåĪ°
    0.24
    æIJª
    0.23
    aviest
    0.23
     recipient
    0.23
     Ug
    0.23
    Activations Density 0.009%

    No Known Activations