© 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. 63294
    Prev
    Next
    INDEX
    Explanations

    perfect and perfection

    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
    ä»Ģä¹Īéĥ½
    -0.10
    oks
    -0.10
    onne
    -0.09
     Fay
    -0.08
    urdy
    -0.08
    edback
    -0.08
    å¹³çŃī
    -0.08
    ç½Ł
    -0.08
    çĦ¦çĤ¹
    -0.08
    aina
    -0.08
    POSITIVE LOGITS
    主ä¹īèĢħ
    0.13
    主義
    0.12
    主ä¹ī
    0.12
    ism
    0.11
    ately
    0.10
    çIJIJ
    0.09
    ality
    0.09
    istas
    0.09
    istic
    0.09
    ist
    0.09
    Activations Density 0.003%

    No Known Activations