© 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. 62703
    Prev
    Next
    INDEX
    Explanations

    and followed by specific verbs

    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
    ä¾Ī
    -0.10
    esi
    -0.08
    andel
    -0.08
    èĤĭ
    -0.08
    kan
    -0.08
    ffects
    -0.07
     jaw
    -0.07
    byn
    -0.07
    ä¾£
    -0.07
    COND
    -0.07
    POSITIVE LOGITS
    ç»ĩ
    0.10
    æĪijæĥ³
    0.09
    è¿Ļä¹Łæĺ¯
    0.09
    ç²¾æ¹Ľ
    0.09
    çªģçł´
    0.09
    ä½Ĩå®ĥ
    0.09
    çĽ
    0.09
    éĩįçĤ¹é¢ĨåŁŁ
    0.09
     Handy
    0.09
    åĩºåı°äºĨ
    0.09
    Activations Density 0.396%

    No Known Activations