© 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. 37500
    Prev
    Next
    INDEX
    Explanations

    numbers followed by words

    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
    	TokenName
    -0.11
    enze
    -0.10
    peare
    -0.09
    udo
    -0.09
    nap
    -0.09
    uchs
    -0.09
    upo
    -0.09
    æİĩ
    -0.09
    ongs
    -0.09
    uset
    -0.09
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.10
    ãģĹãģ¾ãģĦ
    0.09
    rist
    0.09
     noon
    0.08
    lake
    0.08
    ÑĪаÑı
    0.08
    elta
    0.08
    æ©¡
    0.08
    side
    0.08
    -Am
    0.08
    Activations Density 0.200%

    No Known Activations