© 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. 2542
    Prev
    Next
    INDEX
    Explanations

    target audience

    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
    åĹŁ
    -0.09
     kale
    -0.09
     lear
    -0.08
    eti
    -0.08
    ä¸įè§ģ
    -0.08
    лин
    -0.08
    åIJįåŃĹ
    -0.08
    waiting
    -0.07
     Pf
    -0.07
    UCT
    -0.07
    POSITIVE LOGITS
    åıĹä¼Ĺ
    0.19
     target
    0.15
    çļĦ缮æłĩ
    0.14
    缮æłĩ
    0.13
     Target
    0.13
    ç»ĨåĪĨ
    0.13
     audience
    0.13
    éĿ¶
    0.13
    Target
    0.13
    -target
    0.13
    Activations Density 0.064%

    No Known Activations