© 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. 2538
    Prev
    Next
    INDEX
    Explanations

    health

    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
    åŃ£
    -0.10
    æµģæĦŁ
    -0.10
    lit
    -0.09
     viruses
    -0.09
    orsk
    -0.08
    åħħå®ŀ
    -0.08
    æĭ¥
    -0.08
    è¯ķè¯ķ
    -0.08
    isl
    -0.08
     знак
    -0.08
    POSITIVE LOGITS
     hei
    0.10
    æĸ°æĶ¿
    0.09
    éŀį
    0.09
    åIJ±
    0.09
    åĨľçī§
    0.09
    -collar
    0.09
    ennifer
    0.09
    สà¹Ģà¸ķ
    0.09
     Moh
    0.09
    çł´è£Ĥ
    0.09
    Activations Density 0.198%

    No Known Activations