© 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. 112103
    Prev
    Next
    INDEX
    Explanations

    other

    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
    another
    -0.28
    æĭĽèģĺä¿¡æģ¯
    -0.27
     another
    -0.25
     /*#__
    -0.25
    ç©´ä½į
    -0.24
    磸
    -0.24
    åıĪè¦ģ
    -0.24
    ugi
    -0.23
     further
    -0.23
     outra
    -0.23
    POSITIVE LOGITS
    dest
    0.28
    oise
    0.25
     part
    0.25
    iteur
    0.25
     fov
    0.24
    æĹłåı¯
    0.24
    _half
    0.23
    她çļĦ
    0.23
    elight
    0.23
    nock
    0.23
    Activations Density 0.020%

    No Known Activations