© 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. 111228
    Prev
    Next
    INDEX
    Explanations

    learning and skills

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä¿®
    -0.28
    å®ī举
    -0.25
    endum
    -0.25
    å°±è§īå¾Ĺ
    -0.25
    楫
    -0.25
    .Override
    -0.24
    asd
    -0.23
    æłijæŀĿ
    -0.23
    º«
    -0.23
    æĸ¯åŁº
    -0.23
    POSITIVE LOGITS
    éŃĶ
    0.25
    第ä¸ĢæŃ¥
    0.25
    è¿ĻçĤ¹
    0.24
     slee
    0.24
     academy
    0.24
    éĻį
    0.24
     Scientology
    0.24
     drawings
    0.23
    OSC
    0.23
    ç®
    0.23
    Activations Density 0.003%

    No Known Activations