© 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. 23371
    Prev
    Next
    INDEX
    Explanations

    varied text excerpts

    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
     Kills
    -0.28
    educt
    -0.27
     intox
    -0.26
     maneuvers
    -0.24
    ä¸įè¡Į
    -0.24
     embraces
    -0.24
     manoe
    -0.24
    é£İ湿
    -0.24
     thirst
    -0.24
     DAMAGE
    -0.24
    POSITIVE LOGITS
     terminal
    0.28
    Äł
    0.27
    æľ¬æľŁ
    0.26
     tel
    0.26
    osp
    0.25
    èħĭ
    0.25
    à¸ģำ
    0.25
     bu
    0.24
     playing
    0.24
    以ä¸ĭãģ®
    0.24
    Activations Density 0.547%

    No Known Activations