© 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. 88477
    Prev
    Next
    INDEX
    Explanations

    The

    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
    ain
    -0.31
    ation
    -0.30
     commission
    -0.30
    ÅĤo
    -0.28
     fit
    -0.28
     conduct
    -0.26
    称
    -0.25
    dde
    -0.25
     basic
    -0.25
    rian
    -0.25
    POSITIVE LOGITS
    åľ°æĸ¹æĶ¿åºľ
    0.28
     spas
    0.25
     Arms
    0.25
    infeld
    0.25
    (State
    0.25
    åĨ¢
    0.25
    æīĭä¸Ĭ
    0.24
    åĴĮåľ°åĮº
    0.23
     Pants
    0.23
     Peak
    0.23
    Activations Density 0.001%

    No Known Activations