© 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. 24-TRANSCODER-HP
    7. 150279
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     statewide
    -0.32
    åľ¨ç¾İåĽ½
    -0.32
    éĤ£æł·çļĦ
    -0.30
    åĮĹç¾İ
    -0.28
    ç¾İåĨĽ
    -0.28
     familiarity
    -0.27
    ä¸Ńç¾İ
    -0.26
    绿èī²éĢļéģĵ
    -0.26
    åİĨæŶ
    -0.26
    éĤ£æł·
    -0.26
    POSITIVE LOGITS
    å¼ķ
    0.25
    ä¸ĭåįĬ
    0.25
     tied
    0.25
    achs
    0.25
    serter
    0.25
    ĸ
    0.24
     emptied
    0.24
    aching
    0.24
    å¼ķçĪĨ
    0.24
    aky
    0.23
    Activations Density 0.110%

    No Known Activations