© 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. 35700
    Prev
    Next
    INDEX
    Explanations

    food and drink consistency

    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
    åĴĸåķ¡
    -0.10
    âĺķ
    -0.10
     доп
    -0.10
    æĹłæīĢè°ĵ
    -0.10
    åľī
    -0.09
    å±±èĦī
    -0.09
    è·Ħ
    -0.09
    亲å¯Ĩ
    -0.09
    æĽĻ
    -0.09
    ernet
    -0.09
    POSITIVE LOGITS
    å§Ķ
    0.09
     Strauss
    0.09
    åŀ£
    0.09
    åĵį
    0.08
    aky
    0.08
    prec
    0.08
    æ£ĺ
    0.08
    ISTR
    0.08
    _ssl
    0.08
    LLU
    0.08
    Activations Density 0.031%

    No Known Activations