© 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. 38915
    Prev
    Next
    INDEX
    Explanations

    files, organization, set, devices, actions, list

    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
    鲸
    -0.10
    åħ¶ä»ĸçļĦ
    -0.10
    èĢĮä¸į
    -0.09
    ycastle
    -0.09
    çŃ®
    -0.09
    å¤ļåħĥ
    -0.08
    çĨŁ
    -0.08
    PropertyParams
    -0.08
    IFE
    -0.08
    kbd
    -0.08
    POSITIVE LOGITS
    çļĦä¸Ģç§į
    0.12
    æľīä¸Ģå®ļ
    0.10
    usually
    0.09
     usually
    0.09
    .dispatch
    0.08
    éĢļ常
    0.08
    rios
    0.08
     typically
    0.08
    aris
    0.08
    æĶĴ
    0.08
    Activations Density 0.339%

    No Known Activations