© 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. 30766
    Prev
    Next
    INDEX
    Explanations

    code comments or structure

    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
    深深çļĦ
    -0.10
    ä¸Ģä¸ĸ
    -0.09
    çĻ¾åº¦
    -0.09
    缸çĪ±
    -0.09
    ä¸Ī夫
    -0.09
    åľ¨æĪijåĽ½
    -0.09
    第ä¸Ģä½į
    -0.09
    å·ħå³°
    -0.09
    é¦ĸä½į
    -0.09
    丰æĶ¶
    -0.09
    POSITIVE LOGITS
    åħ¨è¿ĩç¨ĭ
    0.09
    ä½Ļ人
    0.09
    以éĺ²
    0.08
     Hab
    0.08
    atra
    0.08
    åİŁæłĩé¢ĺ
    0.08
    çļĦéĴ±
    0.08
    клÑİÑĩен
    0.08
     Lau
    0.07
    _cfg
    0.07
    Activations Density 0.033%

    No Known Activations