© 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. 7286
    Prev
    Next
    INDEX
    Explanations

    saint 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
    è¶Ĭ
    -0.10
     circum
    -0.09
    èĽ©
    -0.09
    æĸ°ä¸Ģè½®
    -0.08
     Federation
    -0.08
     Peanut
    -0.08
    åıªè¦ģæľī
    -0.08
    åħ¬åŃIJ
    -0.08
     мен
    -0.08
    urers
    -0.08
    POSITIVE LOGITS
    _NATIVE
    0.10
    ibr
    0.09
    DCF
    0.09
    æ¶Ĥ
    0.09
     marty
    0.09
    åĩ½
    0.08
    sbin
    0.08
    æľ¬æĬ¥
    0.08
    itag
    0.08
    éĢĶå¾Ħ
    0.08
    Activations Density 0.054%

    No Known Activations