© 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. 5528
    Prev
    Next
    INDEX
    Explanations

    arrow links or citations

    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
    使æĪij
    -0.09
    ÑĮÑı
    -0.09
    èѦæĥķ
    -0.08
    олоÑģ
    -0.08
    ðł
    -0.08
    bang
    -0.08
    æĹ¶å¸¸
    -0.08
    prm
    -0.08
    nik
    -0.08
    åѵåĮĸ
    -0.08
    POSITIVE LOGITS
    åºĶæĶ¶
    0.10
     Transit
    0.09
    ATS
    0.09
    sembles
    0.08
    GRADE
    0.08
    _BYTE
    0.08
    æIJľ
    0.08
    åħļåĴĮ
    0.08
     Tran
    0.08
    ):-
    0.08
    Activations Density 0.028%

    No Known Activations