© 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. 50804
    Prev
    Next
    INDEX
    Explanations

    place names ending in mill, lake, or pond, or road, drive

    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
     Hammer
    -0.10
    æŁĺ
    -0.09
     kad
    -0.09
    elay
    -0.08
    enes
    -0.08
    çŁŃ线
    -0.08
    å§IJå§IJ
    -0.08
    çİĭèĢħ
    -0.08
    åij±
    -0.08
    åĵ¥åĵ¥
    -0.08
    POSITIVE LOGITS
    å·§
    0.10
    临è¿ij
    0.10
    coh
    0.09
    ä¸įæħİ
    0.09
    èį·åħ°
    0.09
    ä¸ļä½Ļ
    0.09
    æģĤ
    0.09
    åľ¨åĨħçļĦ
    0.09
    è¯ĥ
    0.09
    ç¥ī
    0.08
    Activations Density 0.181%

    No Known Activations