© 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. 39635
    Prev
    Next
    INDEX
    Explanations

    restaurants, range, arranged, favorite, Quant

    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¦ı模
    -0.09
    æ¡£
    -0.09
    Inspectable
    -0.09
    è¶ģ
    -0.09
    ãĤĭãĤĪãģĨãģ«
    -0.08
    afia
    -0.08
    Exports
    -0.08
    пеÑĩ
    -0.08
    èµĺ
    -0.08
    eri
    -0.08
    POSITIVE LOGITS
    æľ¬åľ°
    0.11
    Local
    0.08
    .soft
    0.08
    รา
    0.08
    ä»İå°ıå°±
    0.08
    å½ĵåľ°
    0.08
    é²ľæ´»
    0.08
    éĢł
    0.08
    æŶéĹ´åĴĮ
    0.08
    åij±
    0.08
    Activations Density 0.020%

    No Known Activations