© 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. 36839
    Prev
    Next
    INDEX
    Explanations

    assim, im

    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
    楮
    -0.09
    HS
    -0.09
    shore
    -0.09
     latter
    -0.08
    èĨ¨èĥĢ
    -0.08
     handleError
    -0.08
    ASTER
    -0.08
    ãģĹãģ£
    -0.08
    åIJİèĢħ
    -0.07
    æ°¾
    -0.07
    POSITIVE LOGITS
    ilation
    0.11
    äºĨ大éĩıçļĦ
    0.10
    fare
    0.10
    gue
    0.10
    amo
    0.10
    xsd
    0.10
    åĻ¤
    0.09
    大æī¹
    0.09
    æ²IJæµ´
    0.09
    rote
    0.09
    Activations Density 0.007%

    No Known Activations