© 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. 52808
    Prev
    Next
    INDEX
    Explanations

    locations and languages

    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
    ermen
    -0.32
    æłij
    -0.28
    quivo
    -0.27
    èĶĵ
    -0.27
    виз
    -0.26
     cler
    -0.25
    _trees
    -0.25
     trees
    -0.25
     continuum
    -0.25
     ultr
    -0.25
    POSITIVE LOGITS
    toFloat
    0.27
    eton
    0.27
    Thunk
    0.26
    éĽĢ
    0.26
    ican
    0.24
    DialogTitle
    0.24
    focus
    0.24
    enton
    0.24
    ritte
    0.24
     indemn
    0.23
    Activations Density 0.016%

    No Known Activations