© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7603
    Prev
    Next
    INDEX
    Explanations

    Vancouver

    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
    lessly
    -0.12
    ivent
    -0.10
    nuts
    -0.09
    åİŁåĽł
    -0.09
    OrDefault
    -0.09
    ernals
    -0.09
     branching
    -0.09
    обÑĢаз
    -0.09
    ìĤ¬íķŃ
    -0.08
    æĢĽ
    -0.08
    POSITIVE LOGITS
    thur
    0.10
    çĦ¶æĺ¯
    0.09
     Seattle
    0.09
    ized
    0.09
    島
    0.09
    æ¹¾
    0.09
    å²Ľ
    0.09
    lık
    0.08
    izations
    0.08
    maf
    0.08
    Activations Density 0.013%

    No Known Activations