© 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. 23-TRANSCODER-HP
    7. 25383
    Prev
    Next
    INDEX
    Explanations

    Code and references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Generation
    -0.29
    æĺ¯éĿŀ
    -0.27
     Born
    -0.26
     partnerships
    -0.26
    ç»Ļä½łä»¬
    -0.26
    _gradient
    -0.25
    Generation
    -0.24
     relationships
    -0.24
    uples
    -0.24
     Partnership
    -0.24
    POSITIVE LOGITS
    ecs
    0.26
    æĦıè¯Ĩå½¢æĢģ
    0.26
    otive
    0.26
    çŀĴ
    0.24
    iya
    0.24
    acular
    0.24
    Bear
    0.24
    iated
    0.23
    SqlServer
    0.23
    æIJĶ
    0.23
    Activations Density 0.002%

    No Known Activations