© 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. 22034
    Prev
    Next
    INDEX
    Explanations

    parentheses and percentages

    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
    uries
    -0.10
    éĢŀ
    -0.10
    ptions
    -0.10
    court
    -0.10
    ãĥijãĤ¤
    -0.09
    icana
    -0.09
    ëħ¼
    -0.09
    pest
    -0.09
    ithe
    -0.09
    moid
    -0.09
    POSITIVE LOGITS
     Masc
    0.08
    å®ŀè´¨
    0.08
     paren
    0.08
    å§Ĺ
    0.08
     pooled
    0.07
     wag
    0.07
     martin
    0.07
    å®ŀæĻ¯
    0.07
    0
    0.07
    lin
    0.07
    Activations Density 0.355%

    No Known Activations