© 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. 20962
    Prev
    Next
    INDEX
    Explanations

    cloth

    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
    SSION
    -0.10
    orum
    -0.10
    èľĵ
    -0.09
    еÑĩен
    -0.09
    ç§ĭåĨ¬
    -0.09
    qua
    -0.09
     sclerosis
    -0.09
    ложениÑı
    -0.09
    losed
    -0.09
    æĹħé¦Ĩ
    -0.09
    POSITIVE LOGITS
    ãģĹãģ¾ãģĨ
    0.11
    ãģ¾ãģ¾
    0.10
    ening
    0.10
    riv
    0.09
    ozo
    0.09
    ertype
    0.09
    mart
    0.09
    maid
    0.09
    ÅĽci
    0.09
    mates
    0.09
    Activations Density 0.005%

    No Known Activations