© 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. 50281
    Prev
    Next
    INDEX
    Explanations

    referenced thus

    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
    å®ľå±ħ
    -0.10
    ç£Ķ
    -0.09
    缸åĬ©
    -0.08
    æľŃ
    -0.08
    ä¸ĢåľĪ
    -0.08
    æłĵ
    -0.08
    æĻ¯å¾·
    -0.08
     Nug
    -0.08
    lessly
    -0.08
    åĬŀå®ŀäºĭ
    -0.08
    POSITIVE LOGITS
    åIJĪæ³ķ
    0.11
     Buy
    0.09
    makt
    0.09
    buy
    0.09
    æĪIJ人
    0.09
    ç¬ĶèĢħ
    0.08
    isk
    0.08
    axies
    0.08
    å¤Ħå¢ĥ
    0.08
    æĭħ
    0.08
    Activations Density 0.046%

    No Known Activations