© 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. 1970
    Prev
    Next
    INDEX
    Explanations

    concerns and evaluations

    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
    ernal
    -0.08
    毡
    -0.08
    comed
    -0.08
    çĶ¨éĩı
    -0.08
    ój
    -0.08
    ä¿ŀ
    -0.08
    éĤ
    -0.08
    cene
    -0.08
     Helena
    -0.08
    åĤ¬
    -0.08
    POSITIVE LOGITS
    å¾Īéĩįè¦ģ
    0.12
    è¿Ļ对äºİ
    0.12
    éĿŀ常éĩįè¦ģ
    0.11
    è¿Ļä¸ĢçĤ¹
    0.11
    èĩ³åħ³éĩįè¦ģ
    0.10
    ç½ķè§ģ
    0.09
    è¿ĻæĦıåij³çĿĢ
    0.09
     знаÑĩиÑĤ
    0.09
     rarity
    0.09
    åīįæīĢ
    0.09
    Activations Density 0.059%

    No Known Activations