© 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. 9930
    Prev
    Next
    INDEX
    Explanations

    taste and preferences

    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
    æ³Ľ
    -0.09
    æģ¤
    -0.09
    3
    -0.08
    2
    -0.08
    5
    -0.08
    phan
    -0.08
    9
    -0.08
     shoulder
    -0.08
     Nom
    -0.08
    éĶĢ
    -0.08
    POSITIVE LOGITS
    åĵģåij³
    0.21
    åı£åij³
    0.20
    审ç¾İ
    0.20
    åĵģä½į
    0.19
     tastes
    0.19
    åģı好
    0.19
     taste
    0.18
     Taste
    0.17
    åĸľå¥½
    0.17
     preferences
    0.15
    Activations Density 0.068%

    No Known Activations