© 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. 50284
    Prev
    Next
    INDEX
    Explanations

    madness and insanity

    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
    çĵ®
    -0.09
     demás
    -0.09
     Salisbury
    -0.09
    ammen
    -0.08
     Sark
    -0.08
    åѦä¼ļäºĨ
    -0.08
    rees
    -0.08
    çħ¤
    -0.08
    age
    -0.08
    èĢľ
    -0.08
    POSITIVE LOGITS
    ember
    0.11
    èĪ¬çļĦ
    0.11
    atics
    0.10
    0.10
    ously
    0.10
    ç¨ĭ度
    0.09
    uous
    0.09
    trak
    0.09
    -ticket
    0.09
    éĻį临
    0.09
    Activations Density 0.023%

    No Known Activations