© 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. 34732
    Prev
    Next
    INDEX
    Explanations

    made up of

    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
    çªł
    -0.10
    çĪ±å°Ķ
    -0.10
     quo
    -0.09
    éĢIJä¸Ģ
    -0.09
    笳
    -0.08
    å¿ĺè®°äºĨ
    -0.08
    è°©
    -0.08
    åı¯è¾¾
    -0.08
    omin
    -0.08
    纲
    -0.08
    POSITIVE LOGITS
    ç»ĦæĪIJ
    0.13
     ÑģоÑģÑĤоиÑĤ
    0.13
     consists
    0.10
    æŀĦæĪIJ
    0.10
    ç»ĦæĪIJçļĦ
    0.09
    OfYear
    0.09
     ÑģоÑģÑĤав
    0.09
    çĶ±
    0.09
    è¿ĻåIJį
    0.09
     composed
    0.09
    Activations Density 0.106%

    No Known Activations