© 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. 6568
    Prev
    Next
    INDEX
    Explanations

    miles and kilometres

    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
     Sag
    -0.10
     pay
    -0.09
    ä¸Ģä¼ļ
    -0.09
     Pay
    -0.09
    ä¸Ģä¼ļåĦ¿
    -0.08
    ä¸Ģä¸ĭ
    -0.08
     rap
    -0.08
    s
    -0.08
    isor
    -0.08
    ä¸ĢåĪĨéĴŁ
    -0.08
    POSITIVE LOGITS
    檫
    0.13
    /goto
    0.11
    ä¸ĩåħ¬éĩĮ
    0.11
    äºĶåįĥ
    0.10
    ধ
    0.10
    ç£Ķ
    0.10
    åĿ¼
    0.10
    _accepted
    0.10
    _UNLOCK
    0.09
    æŃ£å¸¸ä½¿çĶ¨
    0.09
    Activations Density 0.007%

    No Known Activations