© 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. 111212
    Prev
    Next
    INDEX
    Explanations

    is/was

    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
     loos
    -0.29
     loosen
    -0.26
    æĥĬ人
    -0.25
    è¿Ŀåıį
    -0.25
    each
    -0.25
    that
    -0.25
     marked
    -0.25
     litter
    -0.24
    éĩĮæĸ¯
    -0.24
    cho
    -0.24
    POSITIVE LOGITS
    MITTED
    0.28
    illy
    0.26
    roller
    0.25
    åıijçİ°
    0.24
    æĢ§åij½
    0.24
    iang
    0.23
    дÑĥÑĤ
    0.23
    æĿ¡ä»¶
    0.23
    etchup
    0.23
    رÙģ
    0.23
    Activations Density 0.016%

    No Known Activations