© 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. 23-TRANSCODER-HP
    7. 25537
    Prev
    Next
    INDEX
    Explanations

    Action verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    uding
    -0.30
    emia
    -0.27
    å¼ĥ
    -0.27
    è¦ģä¹Ī
    -0.27
    æŃĩ
    -0.26
    inct
    -0.26
    éĢļè¿ĩ
    -0.26
    ohn
    -0.25
    unction
    -0.25
     dÃłng
    -0.25
    POSITIVE LOGITS
    ︵
    0.28
    è·ŁæĪij
    0.28
     Ob
    0.26
    ç´ĭ
    0.25
    ARY
    0.25
    ary
    0.25
    ipt
    0.25
    åĸ½
    0.24
     jumps
    0.24
    [url
    0.24
    Activations Density 0.036%

    No Known Activations