© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51871
    Prev
    Next
    INDEX
    Explanations

    ready for or ready to

    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
    sWith
    -0.11
    sic
    -0.09
    spy
    -0.09
    кл
    -0.09
    aceous
    -0.09
    panic
    -0.09
     ì§ģìłij
    -0.08
    uality
    -0.08
    nist
    -0.08
    大人
    -0.08
    POSITIVE LOGITS
     sÃłng
    0.12
    rum
    0.10
    æĥķ
    0.10
    æĻĸ
    0.10
    zeitig
    0.09
    abouts
    0.09
    udiant
    0.09
     rÃłng
    0.09
    ught
    0.09
    entious
    0.09
    Activations Density 0.025%

    No Known Activations