© 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. 54453
    Prev
    Next
    INDEX
    Explanations

    of

    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
    igli
    -0.28
     cartridges
    -0.26
    achi
    -0.26
    æĪĺ
    -0.25
    åºıåĪĹ
    -0.25
     crian
    -0.24
     Verd
    -0.24
    archives
    -0.24
    å¿ı
    -0.24
    iant
    -0.24
    POSITIVE LOGITS
    .Ref
    0.32
    amac
    0.28
     flaming
    0.28
    borough
    0.28
    ERING
    0.27
    /wiki
    0.27
     COLL
    0.27
    inks
    0.27
    ENA
    0.26
    .ColumnName
    0.25
    Activations Density 0.015%

    No Known Activations