© 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. 149500
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    çī¹
    -0.27
     ge
    -0.27
    io
    -0.27
    ä¸Ģåıªæīĭ
    -0.26
    o
    -0.26
     medi
    -0.26
     sit
    -0.26
    åľ°ä¸ĭ
    -0.26
     marks
    -0.25
     silver
    -0.25
    POSITIVE LOGITS
    adder
    0.32
    ictionary
    0.31
    éĺ¶å±Ĥ
    0.27
    WARE
    0.27
    mps
    0.26
    Ñĩки
    0.26
    Carthy
    0.26
    adders
    0.25
    ataires
    0.25
    å±ĬæŶ
    0.25
    Activations Density 0.011%

    No Known Activations