© 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. 33-TRANSCODER-HP
    7. 53416
    Prev
    Next
    INDEX
    Explanations

    code and legal text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģåıªæīĭ
    -0.29
     lex
    -0.27
    lite
    -0.25
    樱æ¡ĥ
    -0.25
    Degree
    -0.25
     cleans
    -0.25
    lec
    -0.25
    Evaluate
    -0.25
    éªĿ
    -0.25
    gam
    -0.24
    POSITIVE LOGITS
     additional
    0.29
    é¢Ŀå¤ĸ
    0.28
    umpt
    0.28
     rise
    0.27
    additional
    0.27
    [--
    0.26
    onal
    0.26
    [this
    0.25
    å¯Į
    0.24
     Rise
    0.24
    Activations Density 0.009%

    No Known Activations