© 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. 35-TRANSCODER-HP
    7. 40505
    Prev
    Next
    INDEX
    Explanations

    p

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pants
    -0.27
     immediately
    -0.27
    åįĥåħĥ
    -0.24
    å½±éŁ³
    -0.24
    æľīä¸įå°ij
    -0.24
    æľīåĩłä¸ª
    -0.24
    .getSelection
    -0.24
    dbName
    -0.24
    GetSize
    -0.23
     seats
    -0.23
    POSITIVE LOGITS
    ried
    0.32
    oured
    0.30
    ored
    0.28
    erm
    0.28
    oux
    0.28
    afort
    0.28
    um
    0.27
    igned
    0.27
    oled
    0.27
    ailed
    0.26
    Activations Density 7.794%

    No Known Activations