© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 41111
    Prev
    Next
    INDEX
    Explanations

    attend

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     KIND
    -0.40
    -kind
    -0.40
    Kind
    -0.37
     Kind
    -0.36
     kind
    -0.36
    kind
    -0.35
     Pre
    -0.32
    _kind
    -0.30
    Pre
    -0.29
    åĢĴ
    -0.29
    POSITIVE LOGITS
     createSelector
    0.28
    unner
    0.28
    rophe
    0.27
    éĿĴå°ijå¹´
    0.26
     teenagers
    0.26
    pragma
    0.25
    _instruction
    0.24
    Incoming
    0.24
    Í
    0.24
    een
    0.24
    Activations Density 0.000%

    No Known Activations