© 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. 86871
    Prev
    Next
    INDEX
    Explanations

    Specific entities/technical context

    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
     regrets
    -0.30
    éħ¿
    -0.25
    .hh
    -0.25
    sad
    -0.24
    rarian
    -0.24
    announce
    -0.24
    ROUND
    -0.23
    omed
    -0.23
    Vac
    -0.23
    æ§ģ
    -0.23
    POSITIVE LOGITS
     Sham
    0.27
    gue
    0.26
    lineno
    0.25
    æĬĬ她
    0.25
    lesh
    0.24
    éĹ¾
    0.24
     closer
    0.24
     differentiation
    0.24
    ↵↵↵↵
    0.24
     prompt
    0.23
    Activations Density 0.000%

    No Known Activations