© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10170
    Prev
    Next
    INDEX
    Explanations

    Mule ESB services

    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
     дол
    -0.10
    faker
    -0.10
    è´Ńç½®
    -0.09
    æ¼Ķç»ĥ
    -0.09
    OOD
    -0.09
    ìĤŃ
    -0.09
    unders
    -0.09
    æľºçĶµ
    -0.08
    æ¼ĶåĶ±
    -0.08
    çĻĸ
    -0.08
    POSITIVE LOGITS
    æĮij
    0.10
    对å¤ĸå¼ĢæĶ¾
    0.10
    èĿ¶
    0.09
    å¼ĢæĶ¾
    0.09
    .bpm
    0.08
    æ»´
    0.08
    é«ĺéĢŁåıijå±ķ
    0.08
    è¢ħ
    0.08
    .sap
    0.08
    ä¾ĭå¤ĸ
    0.08
    Activations Density 0.211%

    No Known Activations