© 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. 58499
    Prev
    Next
    INDEX
    Explanations

    relevance of concepts

    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
    èĵ¦
    -0.10
    æ½ľèĥ½
    -0.09
    åĨĢ
    -0.08
    åŃIJå¼Ł
    -0.08
    è§ĩ
    -0.08
    lar
    -0.08
    éļħ
    -0.08
    ElementType
    -0.08
    åŁºæľ¬æĥħåĨµ
    -0.08
     Bene
    -0.08
    POSITIVE LOGITS
    levance
    0.11
     relevance
    0.11
    ancement
    0.10
    itim
    0.10
    icit
    0.09
    çģ¼
    0.09
    auce
    0.09
     Geh
    0.09
    ICA
    0.08
     distracting
    0.08
    Activations Density 0.018%

    No Known Activations