© 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. 52898
    Prev
    Next
    INDEX
    Explanations

    run

    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
    yleft
    -0.29
    ãĤĭãĤĤãģ®
    -0.28
    ãĥ¼ãĥĹ
    -0.27
     affine
    -0.25
    xcb
    -0.25
    xdf
    -0.25
    ormap
    -0.25
     copyrighted
    -0.25
    ymmetric
    -0.24
    urtle
    -0.24
    POSITIVE LOGITS
    RS
    0.28
    bs
    0.28
    rs
    0.27
    it
    0.27
    oya
    0.27
     BS
    0.27
     IX
    0.26
     bs
    0.26
     RS
    0.26
     channel
    0.25
    Activations Density 0.009%

    No Known Activations