© 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. 62098
    Prev
    Next
    INDEX
    Explanations

    place 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
    uba
    -0.10
    _lc
    -0.10
    åħ±åĪĽ
    -0.09
    avors
    -0.09
    HING
    -0.09
    loff
    -0.09
    pedia
    -0.09
    PAD
    -0.09
    åĴ¸
    -0.09
    pad
    -0.09
    POSITIVE LOGITS
    ÙĪØ·
    0.09
    OTA
    0.09
    æĦī
    0.09
    éĶIJ
    0.09
    享åıĹåĪ°
    0.09
    çĿ
    0.08
    é¦ĸæī¹
    0.08
    ä¹ĭä¸Ń
    0.08
    åħ¶æ¬¡æĺ¯
    0.08
    轫
    0.08
    Activations Density 0.007%

    No Known Activations