© 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. 151395
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
     shop
    -0.31
    qli
    -0.28
    dem
    -0.26
    sat
    -0.26
    rec
    -0.26
     rec
    -0.26
    æ¯ķ
    -0.25
     notice
    -0.25
    çĮ®
    -0.25
    ople
    -0.24
    POSITIVE LOGITS
    è´¥
    0.28
    éĥ½èĥ½å¤Ł
    0.27
     honoured
    0.26
    èħIJè´¥
    0.26
    _slot
    0.25
     *}
    0.24
    éī´
    0.24
    iates
    0.23
    Slot
    0.23
    æķĹ
    0.23
    Activations Density 0.527%

    No Known Activations