© 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. 39896
    Prev
    Next
    INDEX
    Explanations

    Harry Potter

    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
    ç¦ıçī¹
    -0.10
    .gwt
    -0.09
    _presence
    -0.09
     Ðijог
    -0.09
    èĤ¢
    -0.09
    身ä½ĵåģ¥åº·
    -0.09
    åģķ
    -0.09
    ç¼£
    -0.09
    å¤ĸæı´
    -0.09
    çĻ½èıľ
    -0.08
    POSITIVE LOGITS
    allocate
    0.09
    ALLOC
    0.08
    å¯Ĵ
    0.08
    河水
    0.08
     POT
    0.08
     Hed
    0.08
    ä¸įéĻIJ
    0.08
    cmb
    0.08
    aji
    0.08
     hypo
    0.08
    Activations Density 0.050%

    No Known Activations