© 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. 151273
    Prev
    Next
    INDEX
    Explanations

    apr

    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
     Citation
    -0.26
    arith
    -0.25
    èĻ¹
    -0.24
    aris
    -0.24
    æĿ¥çĶµ
    -0.24
    ipsis
    -0.23
    arrow
    -0.23
    PID
    -0.23
    itar
    -0.23
    elps
    -0.23
    POSITIVE LOGITS
    coles
    0.26
    igua
    0.24
    ries
    0.23
    第ä¸Ģ家
    0.23
    shall
    0.23
    è´¨éĩıåĴĮ
    0.23
    éļ§
    0.23
    åĢºæĿĥ
    0.23
    .stat
    0.23
    çĶ¨äºº
    0.23
    Activations Density 0.613%

    No Known Activations