© 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. 1613
    Prev
    Next
    INDEX
    Explanations

    signatures and patterns

    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
    æİ¥åĬĽ
    -0.09
    OMPI
    -0.09
    UNC
    -0.09
    ساء
    -0.08
    çļĦè§Ĵèī²
    -0.08
    asant
    -0.08
    åIJī祥
    -0.08
    èĩªåĬ©
    -0.08
    éºĭ
    -0.08
    ób
    -0.08
    POSITIVE LOGITS
    çĹķ迹
    0.17
     signature
    0.16
     signatures
    0.15
    signature
    0.15
    Signature
    0.12
     patterns
    0.12
    è¯ģæį®
    0.12
    _signature
    0.12
     Signature
    0.11
    Pattern
    0.11
    Activations Density 0.246%

    No Known Activations