© 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. 22-TRANSCODER-HP
    7. 97075
    Prev
    Next
    INDEX
    Explanations

    impact, striking, contact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    lient
    -0.28
    ·»
    -0.27
    TEX
    -0.27
    reds
    -0.26
    åij½
    -0.26
    ä¸įä¸ĭ
    -0.26
    aira
    -0.25
    éļ°
    -0.25
    aturing
    -0.25
    éĽ¢ãĤĮ
    -0.25
    POSITIVE LOGITS
    æķ²
    0.28
    çł°
    0.27
    ä¾Ŀæį®
    0.26
    çĬĢ
    0.26
     banks
    0.26
    åī§çĥĪ
    0.26
    Ñĩки
    0.26
    ÑĥÑĪки
    0.25
    声éģĵ
    0.25
    åī²
    0.25
    Activations Density 0.018%

    No Known Activations