© 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. 20414
    Prev
    Next
    INDEX
    Explanations

    numbers followed by Base or calorie

    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
    enstein
    -0.11
    åı¯è§Ĥ
    -0.10
    ç§ijæĬĢèĤ¡ä»½
    -0.09
    ðŁı»
    -0.09
    lyn
    -0.09
    รม
    -0.09
    çĤķ
    -0.09
    _SI
    -0.09
     sexes
    -0.09
    ances
    -0.09
    POSITIVE LOGITS
    ç³Ĭæ¶Ĥ
    0.09
    为æѤ
    0.09
    IZED
    0.09
     mile
    0.09
    æģĤ
    0.09
    ized
    0.08
    urator
    0.08
    -plus
    0.08
    mile
    0.08
    ä»İæѤ
    0.08
    Activations Density 0.121%

    No Known Activations