© 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. 34995
    Prev
    Next
    INDEX
    Explanations

    detection and testing

    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
    TYPO
    -0.09
    ç¦ģ
    -0.09
    åħ¸åŀĭ
    -0.09
    _IB
    -0.09
    èµ°è·¯
    -0.09
    Æ°u
    -0.09
    enso
    -0.09
    xab
    -0.08
    oa
    -0.08
    ABILITY
    -0.08
    POSITIVE LOGITS
    æĬ½æ£Ģ
    0.17
    è¶ħæłĩ
    0.14
    æ£ĢéªĮ
    0.14
    çĽijæµĭ
    0.14
    æĬ½æŁ¥
    0.13
    æ£Ģæµĭ
    0.13
    ä¸įåIJĪæł¼
    0.12
    è´¨æ£Ģ
    0.12
    çĽijæݧ
    0.10
     testing
    0.10
    Activations Density 0.127%

    No Known Activations