© 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. 33-TRANSCODER-HP
    7. 52895
    Prev
    Next
    INDEX
    Explanations

    brain

    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
    ANG
    -0.26
    aved
    -0.26
    _flutter
    -0.25
     trot
    -0.25
    以为
    -0.24
    rowse
    -0.24
    engo
    -0.23
    assoc
    -0.23
     St
    -0.23
    *l
    -0.23
    POSITIVE LOGITS
    é¾Ī
    0.26
    (_.
    0.26
    LOOD
    0.25
    iform
    0.25
    é³ĥ
    0.25
    ÑĪие
    0.25
     Abbas
    0.25
    Ken
    0.25
    chaft
    0.24
    /question
    0.24
    Activations Density 0.007%

    No Known Activations