© 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. 111218
    Prev
    Next
    INDEX
    Explanations

    have

    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
     nämlich
    -0.27
    wards
    -0.26
    çİĩåħĪ
    -0.24
    yet
    -0.24
    vik
    -0.24
    loi
    -0.24
    mere
    -0.24
    amps
    -0.23
     Lump
    -0.23
    udents
    -0.23
    POSITIVE LOGITS
    足迹
    0.25
    adin
    0.25
     aver
    0.24
     mend
    0.24
    æĮŁ
    0.23
    人çĶŁçļĦ
    0.23
    åĸľæ¬¢åIJĥ
    0.23
    æİ£
    0.23
    èģ¿
    0.23
     Sinn
    0.23
    Activations Density 0.006%

    No Known Activations