© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9671
    Prev
    Next
    INDEX
    Explanations

    Gary followed by name

    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
    楮
    -0.12
    å·¢
    -0.10
    ively
    -0.10
    iw
    -0.10
    äºĨèĩªå·±çļĦ
    -0.09
    aries
    -0.09
    ÑĤ
    -0.09
    æĻ°
    -0.09
    åĨįçĶŁèĥ½æºIJ
    -0.09
    ç¾¹
    -0.08
    POSITIVE LOGITS
    0.12
    ness
    0.11
    ono
    0.10
    ingly
    0.09
    åŀĽ
    0.09
    olk
    0.08
    olds
    0.08
    ification
    0.08
    anne
    0.08
    ying
    0.08
    Activations Density 0.007%

    No Known Activations