© 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. 11556
    Prev
    Next
    INDEX
    Explanations

    taste descriptors

    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
    .dot
    -0.09
    çİ©
    -0.09
    ä¼ij
    -0.09
     Nhi
    -0.09
    tober
    -0.09
    çĸ¯
    -0.09
    æ¤į
    -0.08
    èĦ¸
    -0.08
    æ´Ĺæīĭ
    -0.08
    ocs
    -0.08
    POSITIVE LOGITS
    èĭ¦
    0.21
    æ»ĭåij³
    0.17
     taste
    0.17
    åij³éģĵ
    0.16
    çĶľ
    0.16
     sweetness
    0.14
     tastes
    0.14
    åij³
    0.14
     Taste
    0.14
    sweet
    0.14
    Activations Density 0.040%

    No Known Activations