© 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. 58161
    Prev
    Next
    INDEX
    Explanations

    auxiliary, accessories, supporting

    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
    olec
    -0.10
    миÑĢ
    -0.09
    åıĮéĩį
    -0.09
    鸳
    -0.08
    åįĬ个æľĪ
    -0.08
    åħ¨å¤©
    -0.08
     Willow
    -0.08
    è·¯ç¨ĭ
    -0.08
    abric
    -0.08
    çİ°æľīçļĦ
    -0.08
    POSITIVE LOGITS
    è¾ħåĬ©
    0.18
    éħįå¥Ĺ
    0.17
    éħį件
    0.16
    éĻĦå±ŀ
    0.16
    è¾ħ
    0.15
    è¼Ķ
    0.14
    aux
    0.14
     accessories
    0.14
    Aux
    0.13
     supporting
    0.13
    Activations Density 0.118%

    No Known Activations