© 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. 51088
    Prev
    Next
    INDEX
    Explanations

    except, exception, aside, apart

    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
    åIJĦ级
    -0.10
     supposedly
    -0.10
    .RemoveAll
    -0.09
    rlen
    -0.09
    æľīç§į
    -0.08
    too
    -0.08
    çŃĶé¢ĺ
    -0.08
    çģ«èĬ±
    -0.08
    _lengths
    -0.08
    rogen
    -0.08
    POSITIVE LOGITS
    ä¾ĭå¤ĸ
    0.27
     exceptions
    0.21
     exception
    0.20
     except
    0.20
    except
    0.19
    éĻ¤å¤ĸ
    0.18
    exceptions
    0.17
     Exceptions
    0.17
    Exceptions
    0.15
     Except
    0.15
    Activations Density 0.058%

    No Known Activations