© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34403
    Prev
    Next
    INDEX
    Explanations

    anecdotal evidence

    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
    ieur
    -0.09
    itarian
    -0.08
    patrick
    -0.08
    utes
    -0.08
    avr
    -0.08
    uard
    -0.08
    baugh
    -0.08
    Exclusive
    -0.08
     anniversary
    -0.08
    ucha
    -0.08
    POSITIVE LOGITS
    滥
    0.11
     anecd
    0.10
    å¼ı
    0.10
    åĴĮæĬĢæľ¯
    0.09
    å¼ıçļĦ
    0.09
    轶
    0.09
    illus
    0.09
    åµĺ
    0.09
    IRD
    0.09
    oman
    0.09
    Activations Density 0.007%

    No Known Activations