© 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. 50176
    Prev
    Next
    INDEX
    Explanations

    effects of

    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
    念
    -0.10
    تÙĥ
    -0.10
    è¯Ī
    -0.08
    çļĦæľĢåIJİä¸Ģ
    -0.08
    笼
    -0.08
    anko
    -0.08
    åIJĮæŶè¿ĺ
    -0.08
    æĭĹ
    -0.08
    ä¹ĭ称
    -0.08
     prefix
    -0.08
    POSITIVE LOGITS
     Effects
    0.12
    æķĪåºĶ
    0.12
     effects
    0.11
    Effects
    0.09
    effects
    0.09
    _effects
    0.09
    éģĹ
    0.09
     effect
    0.09
    å®Ĺ
    0.09
     arte
    0.09
    Activations Density 0.069%

    No Known Activations