© 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. 50729
    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
    çī¹æľīçļĦ
    -0.08
     bel
    -0.08
    æīĭæĮĩ
    -0.08
    é¦Ļåij³
    -0.08
    med
    -0.08
    åıijå±ķè§ĦåĪĴ
    -0.08
    é£İéĩĩ
    -0.08
     prefer
    -0.08
    åĩij
    -0.08
    re
    -0.07
    POSITIVE LOGITS
    иÑĪ
    0.11
    он
    0.11
    _LSB
    0.10
    ahead
    0.10
    getOption
    0.10
    WithValue
    0.09
    å¸ı
    0.09
    èĸ®
    0.09
    ê»ı
    0.09
    ussen
    0.09
    Activations Density 0.005%

    No Known Activations