© 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. 8294
    Prev
    Next
    INDEX
    Explanations

    color combinations, Organization yet, care for

    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
    ç¼Ĩ
    -0.08
    å°»
    -0.08
    éľ²å¤©
    -0.08
    ائÙħ
    -0.08
    çķ¢ç«Ł
    -0.07
    æ¯ķç«Ł
    -0.07
    çĪ
    -0.07
    åľ¨æĪij
    -0.07
    (PropertyName
    -0.07
    ä¸įä½İäºİ
    -0.07
    POSITIVE LOGITS
    okie
    0.09
    ghost
    0.09
    ests
    0.09
    ç§ijæĬĢåĽŃ
    0.09
    åĬŀäºĭå¤Ħ
    0.09
    饰
    0.09
    åĩ¸
    0.08
    hort
    0.08
    -preview
    0.08
    饲
    0.08
    Activations Density 0.040%

    No Known Activations