© 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. 11473
    Prev
    Next
    INDEX
    Explanations

    candidate for consideration

    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
    imitive
    -0.10
    éĻĮ
    -0.10
    è¿·æĥij
    -0.09
    éĴł
    -0.09
    èĩ´åĬĽäºİ
    -0.09
    _tac
    -0.09
    uur
    -0.09
    ноÑģÑĤ
    -0.09
    .lin
    -0.09
    è¿Ļåıª
    -0.09
    POSITIVE LOGITS
    åĪĨéħį
    0.10
    olem
    0.09
    ç»´å°Ķ
    0.09
    ç½ij讯
    0.09
    éĢģä¸Ĭ
    0.09
    went
    0.09
    Õ¾
    0.09
    èĨ»
    0.08
    ymb
    0.08
    æ³IJ
    0.08
    Activations Density 0.040%

    No Known Activations