© 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. 149208
    Prev
    Next
    INDEX
    Explanations

    Om

    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
    Negative Logits
    uitive
    -0.25
    _throw
    -0.25
    åĨ³çŃĸ
    -0.24
    ä½Ĩ她
    -0.24
    anse
    -0.24
    avad
    -0.24
    é²ľæĺİ
    -0.23
    çĶ¨æĪ·æıIJä¾Ľ
    -0.23
    rouw
    -0.23
    	rep
    -0.23
    POSITIVE LOGITS
     nested
    0.26
     expanding
    0.25
    èĭij
    0.24
     utility
    0.24
    TimeString
    0.24
    outer
    0.24
    еÑĢе
    0.24
     expansion
    0.24
    amento
    0.24
    ERICA
    0.24
    Activations Density 1.394%

    No Known Activations