© 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. 38119
    Prev
    Next
    INDEX
    Explanations

    string comparison

    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
    è´½
    -0.11
    è°¤
    -0.10
    ç«ĭæ³ķ
    -0.09
    ä¸ĢæŃ¥
    -0.09
    åĪĹ举
    -0.09
    _pref
    -0.09
    ought
    -0.09
    rous
    -0.09
    åĬĿ
    -0.09
    åij¼
    -0.09
    POSITIVE LOGITS
    IgnoreCase
    0.10
     StringComparison
    0.10
    åĨ³èĥľ
    0.09
    _COMPARE
    0.09
    ASTE
    0.09
    æĥļ
    0.09
    .Equal
    0.09
    _EQUAL
    0.09
    åĸľæ¬¢åIJĥ
    0.09
    .Criteria
    0.09
    Activations Density 0.247%

    No Known Activations