© 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. 25-TRANSCODER-HP
    7. 109323
    Prev
    Next
    INDEX
    Explanations

    Barack

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éģĵ
    -0.29
    zh
    -0.29
    pher
    -0.28
    åĬ¨
    -0.28
    orientation
    -0.27
     zh
    -0.25
     along
    -0.25
    æĸ¹ä½į
    -0.25
     shall
    -0.24
    zt
    -0.24
    POSITIVE LOGITS
    een
    0.29
    åĽŀæĿ¥äºĨ
    0.28
    scoped
    0.28
    idency
    0.26
    è³ŀ
    0.25
    rego
    0.24
    egral
    0.24
    еÑĢÑĭ
    0.24
    sei
    0.24
    æŀľåĽŃ
    0.24
    Activations Density 0.249%

    No Known Activations