© 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. 10032
    Prev
    Next
    INDEX
    Explanations

    to followed by a noun

    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
    ä¹Łåľ¨
    -0.10
    atham
    -0.10
     Whip
    -0.09
    èĬĿåĬłåĵ¥
    -0.09
    akin
    -0.09
    .Types
    -0.09
    å¥ij
    -0.08
    \Component
    -0.08
    apus
    -0.08
    /html
    -0.08
    POSITIVE LOGITS
    åĩĢèµĦ产
    0.08
    çļĦæĺ¯
    0.08
    äº
    0.08
    _SETUP
    0.08
    æŁĶæĢ§
    0.08
    SUR
    0.08
    _DOT
    0.08
    NST
    0.08
     Grove
    0.08
    ató
    0.08
    Activations Density 0.113%

    No Known Activations