© 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. 52398
    Prev
    Next
    INDEX
    Explanations

    Weinstein, Weinberg, Feinstein, Pratt

    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
    ARNING
    -0.10
    otor
    -0.10
    åĽ«
    -0.09
     Isles
    -0.09
    IDL
    -0.09
    æ±Ľ
    -0.09
    ·»
    -0.09
    éľĵ
    -0.09
    tons
    -0.09
    尽头
    -0.09
    POSITIVE LOGITS
    ä¹İ
    0.11
    ä¸Ģ个éĹ®é¢ĺ
    0.10
    adt
    0.08
    æĭŃ
    0.08
    shr
    0.08
    yc
    0.08
    lé
    0.08
     assorted
    0.08
    ucher
    0.07
     Berm
    0.07
    Activations Density 0.005%

    No Known Activations