© 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. 33672
    Prev
    Next
    INDEX
    Explanations

    sort of / kind of phrases

    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
    çģĮ
    -0.10
    æŁ¬
    -0.09
    енко
    -0.09
    åIJİèĢħ
    -0.09
    jc
    -0.09
    Assignable
    -0.08
    dyn
    -0.08
    å®Ļ
    -0.08
    ä¸Ŀ绸
    -0.08
    ä»įçĦ¶æĺ¯
    -0.08
    POSITIVE LOGITS
     Kear
    0.09
    amo
    0.09
    è¨Ģ
    0.09
    档次
    0.08
    ä¸į大
    0.08
    asil
    0.08
    ä¸ĵéĹ¨ä¸º
    0.08
    èĮ«çĦ¶
    0.08
    prech
    0.08
    éĺ´
    0.08
    Activations Density 0.048%

    No Known Activations