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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7951
    Prev
    Next
    INDEX
    Explanations

    comparison with than

    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
    lessly
    -0.09
    igi
    -0.08
    æ¢ħèĬ±
    -0.08
     Pine
    -0.08
    åĥ»
    -0.08
    _rng
    -0.07
    åĺī
    -0.07
    å¥ī
    -0.07
     tÃłi
    -0.07
    çѱ
    -0.07
    POSITIVE LOGITS
     than
    0.15
    than
    0.13
    åĿŀ
    0.11
    äºİ
    0.11
    _than
    0.10
    æ¯ĶåĪ©
    0.10
    æ¯Ķ
    0.09
    _THAN
    0.09
    Than
    0.09
    æ¯Ķäºļ
    0.09
    Activations Density 0.149%

    No Known Activations