© 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. 53530
    Prev
    Next
    INDEX
    Explanations

    study

    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
    å¤ļ项
    -0.30
    isphere
    -0.30
    _DRV
    -0.26
    Reviews
    -0.25
    _controls
    -0.25
    emacs
    -0.25
     Dra
    -0.24
    两项
    -0.24
    owane
    -0.24
    ç¾ŀ
    -0.24
    POSITIVE LOGITS
     study
    1.54
     Study
    1.26
    study
    1.23
    Study
    1.15
    _study
    0.98
     estudio
    0.89
    çłĶ究
    0.88
    .study
    0.81
     studying
    0.63
    udy
    0.59
    Activations Density 0.238%

    No Known Activations