© 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. 22255
    Prev
    Next
    INDEX
    Explanations

    Pope names

    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
    ummy
    -0.09
    ss
    -0.09
    容è²Į
    -0.09
    åŃIJéĩĮ
    -0.09
    éħIJ
    -0.08
     khỼp
    -0.08
    UDA
    -0.08
    nde
    -0.08
    ARA
    -0.08
     beh
    -0.08
    POSITIVE LOGITS
    ðŁı»
    0.09
    æ¤ħ
    0.09
    zilla
    0.09
    erty
    0.09
    å°¼äºļ
    0.09
    Trivia
    0.09
    omo
    0.09
    erties
    0.09
    pline
    0.09
    yes
    0.09
    Activations Density 0.004%

    No Known Activations