© 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. 24-TRANSCODER-HP
    7. 149534
    Prev
    Next
    INDEX
    Explanations

    field

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĪка
    -0.29
    æĽ¿
    -0.26
    urve
    -0.25
    InstanceState
    -0.24
    енÑĮк
    -0.23
    eki
    -0.23
    ffa
    -0.23
    槽
    -0.23
    pies
    -0.23
     suitcase
    -0.23
    POSITIVE LOGITS
    lights
    0.27
    renched
    0.26
    lessly
    0.26
    igan
    0.26
    lessness
    0.25
    swith
    0.25
    less
    0.25
     deg
    0.25
    erman
    0.25
    ern
    0.24
    Activations Density 2.552%

    No Known Activations