© 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. 7780
    Prev
    Next
    INDEX
    Explanations

    hometown

    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
    ment
    -0.10
    ments
    -0.08
    ly
    -0.08
    inning
    -0.08
    holder
    -0.08
    woman
    -0.07
     nations
    -0.07
    åĮºåĨħ
    -0.07
    room
    -0.07
    pointer
    -0.07
    POSITIVE LOGITS
    åģļæ³ķ
    0.10
    å¼Ģæľº
    0.10
     коÑĤоÑĢого
    0.10
    æĢ¿
    0.10
    annah
    0.10
    fra
    0.09
    ÑĢез
    0.09
    ippo
    0.09
    iena
    0.09
    tractor
    0.09
    Activations Density 0.005%

    No Known Activations