© 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. 58900
    Prev
    Next
    INDEX
    Explanations

    race, breed, species, sexes

    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
    irt
    -0.10
    çŃĸ
    -0.09
    èĢģ人
    -0.09
    è¿Ļä½į
    -0.08
    è°ĥåĬ¨
    -0.08
    cascade
    -0.08
     DJ
    -0.08
    æݪ
    -0.08
    adle
    -0.08
    å·§
    -0.08
    POSITIVE LOGITS
    çī©ç§į
    0.14
     species
    0.14
     Species
    0.13
    åĵģç§į
    0.12
    species
    0.12
    èĬ±çº¹
    0.12
    ç§įç±»
    0.12
    ç±»åŀĭ
    0.12
    _species
    0.12
    Species
    0.12
    Activations Density 0.142%

    No Known Activations