© 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. 6933
    Prev
    Next
    INDEX
    Explanations

    possible combinations or permutations

    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
     Bucc
    -0.09
    è¿Ī
    -0.09
     Biggest
    -0.09
    ocab
    -0.09
     ÑĤоÑĢ
    -0.09
    çłľ
    -0.08
     asses
    -0.08
    Domains
    -0.08
    usa
    -0.08
    ReturnValue
    -0.08
    POSITIVE LOGITS
     possible
    0.16
    possible
    0.13
    åı¯èĥ½æĢ§
    0.12
     Possible
    0.12
     possibilities
    0.12
     possibile
    0.12
     возмож
    0.12
    ç©·
    0.12
    æİĴåĪĹ
    0.12
    Possible
    0.11
    Activations Density 0.244%

    No Known Activations