© 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. 62407
    Prev
    Next
    INDEX
    Explanations

    abstract : word

    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
    åĽºçĦ¶
    -0.08
    ä¸įä½ı
    -0.08
    inden
    -0.08
    æŃ»è§Ĵ
    -0.07
    ROID
    -0.07
    ess
    -0.07
     endregion
    -0.07
    æ³ł
    -0.07
    ä¸įçķĻ
    -0.07
     /*<<<
    -0.07
    POSITIVE LOGITS
    èıĸ
    0.08
     Hamp
    0.08
    åįģæĿ¡
    0.08
    BOOLE
    0.07
    [@"
    0.07
     tph
    0.07
    chine
    0.07
    _aa
    0.07
    Camb
    0.07
    缯
    0.07
    Activations Density 0.191%

    No Known Activations