© 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. 112522
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åħĶ
    -0.24
    ç§Ģ
    -0.23
    ầ
    -0.23
    _hide
    -0.23
    驹
    -0.22
    æĹ¥èĩ³
    -0.22
    æĹ¥ä¸ĭåįĪ
    -0.21
    ç¿Ĭ
    -0.21
    请éĢīæĭ©
    -0.21
    çļĦæ¦Ĥ念
    -0.21
    POSITIVE LOGITS
    ä¹Łå°±
    0.25
    .magnitude
    0.24
    ApplicationContext
    0.23
     ~~
    0.23
    ç¦ģ
    0.23
     ende
    0.23
    eph
    0.23
    æݨ
    0.22
    éģıåĪ¶
    0.22
    Magnitude
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.