© 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. 31608
    Prev
    Next
    INDEX
    Explanations

    removal, elimination, solved

    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
    æ¿ij
    -0.09
    xdb
    -0.09
    é¢ijç¹ģ
    -0.09
     gravity
    -0.08
    olated
    -0.08
    ä¸įä»ħè¦ģ
    -0.08
    äºĨ大éĩıçļĦ
    -0.08
    Ñĩки
    -0.08
    å¹³åĿĩæ¯ı
    -0.08
    æī§
    -0.08
    POSITIVE LOGITS
    æ¶ĪéĻ¤
    0.13
    æ¶ĪçģŃ
    0.12
    æ¸ħéĻ¤
    0.11
     removal
    0.11
    转åıĺ为
    0.11
     elimination
    0.11
    åİ»éĻ¤
    0.10
    elim
    0.10
    Handled
    0.10
    åĮĸ解
    0.10
    Activations Density 0.177%

    No Known Activations