© 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. 23715
    Prev
    Next
    INDEX
    Explanations

    disclaimers and requirements

    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
    Not in Any Lists

    No Comments

    Negative Logits
     be
    -0.32
     carefully
    -0.30
    好好
    -0.29
    á¹Ń
    -0.28
    åħ·å¤ĩ
    -0.27
    è°¨æħİ
    -0.27
     proportion
    -0.25
    åİī
    -0.25
     careful
    -0.25
    èѦæĥķ
    -0.25
    POSITIVE LOGITS
    éľĢè¦ģ
    0.67
    åºĶ该
    0.58
    å¿ħé¡»
    0.56
     needed
    0.55
    éľĢ
    0.53
    åºĶå½ĵ
    0.53
    åºĶ该æĺ¯
    0.52
     need
    0.50
    ä½łéľĢè¦ģ
    0.49
    å¿ħéłĪ
    0.49
    Activations Density 0.003%

    No Known Activations