© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36877
    Prev
    Next
    INDEX
    Explanations

    participate in

    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
    åĬŁå¤«
    -0.11
    sey
    -0.09
    fort
    -0.09
    оÑģÑĮ
    -0.09
    ä¸įåĩº
    -0.09
    å®ŀåĬĽ
    -0.09
    ìĹŃ
    -0.09
    ifier
    -0.09
    /or
    -0.09
    溲
    -0.09
    POSITIVE LOGITS
    ively
    0.10
    çĦī
    0.09
    -minded
    0.09
     minded
    0.09
    åħ¨åĽ½äººæ°ij
    0.09
    IVITY
    0.09
    anh
    0.09
    ookie
    0.08
    organ
    0.08
     ún
    0.08
    Activations Density 0.011%

    No Known Activations