© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18361
    Prev
    Next
    INDEX
    Explanations

    locomotive or steam engines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä»°
    -0.09
    çĶµåŃIJ产åĵģ
    -0.09
     Mr
    -0.08
    ek
    -0.08
     pierced
    -0.08
    çĢij
    -0.08
    atform
    -0.08
    éĿĻèĦī
    -0.08
    åıĺäºĨ
    -0.08
    ç¾½æ¯ĽçIJĥ
    -0.08
    POSITIVE LOGITS
    马æĭī
    0.12
    èĴ¸æ±½
    0.12
    轨
    0.11
    åĪĹ车
    0.10
    coal
    0.10
    .getB
    0.10
    è¾Ļ
    0.10
    轨éģĵ交éĢļ
    0.10
    ðŁļĤ
    0.10
     steam
    0.10
    Activations Density 0.154%

    No Known Activations