© 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. 23656
    Prev
    Next
    INDEX
    Explanations

    of

    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
     paste
    -0.28
     above
    -0.26
    _DELETE
    -0.25
    没æĶ¶
    -0.25
    修订
    -0.25
    è´¨éĩıéĹ®é¢ĺ
    -0.25
    èĢĮæĪIJ
    -0.24
     sails
    -0.24
     blames
    -0.24
    ponde
    -0.24
    POSITIVE LOGITS
    egt
    0.28
    URT
    0.27
    Lorem
    0.26
    TRL
    0.25
     Escorts
    0.25
    aid
    0.25
    å½ĵä¹ĭ
    0.25
     gaining
    0.25
    _ft
    0.25
     ultimately
    0.24
    Activations Density 0.011%

    No Known Activations