© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7390
    Prev
    Next
    INDEX
    Explanations

    league names

    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
    locker
    -0.09
    åł¡åŀĴ
    -0.09
    inal
    -0.09
    åĢŁéĴ±
    -0.09
    åħĦå¼Ł
    -0.09
    ä¸ĭåįķ
    -0.09
    åĬłå¿«åıijå±ķ
    -0.08
    éļIJ约
    -0.08
    å¸ĪèĮĥ
    -0.08
    arak
    -0.08
    POSITIVE LOGITS
    èģĶèµĽ
    0.11
    æ°´åĩĨ
    0.10
    umb
    0.09
    observer
    0.09
    è¡Ķ
    0.08
    ä¸įåĪĨ
    0.08
    åĹ¡
    0.08
    .expect
    0.08
     Tier
    0.08
    LEV
    0.08
    Activations Density 0.229%

    No Known Activations