© 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. 2026
    Prev
    Next
    INDEX
    Explanations

    spaced, separated, interval, between

    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
    _UUID
    -0.10
    otics
    -0.10
    æīĭèħķ
    -0.10
    åīįæĸ¹
    -0.09
     полÑĥÑĩа
    -0.09
     Ames
    -0.08
    outline
    -0.08
    åIJ
    -0.08
    è§ģæķĪ
    -0.08
    spl
    -0.08
    POSITIVE LOGITS
    æĹ¶ç©º
    0.10
     mere
    0.09
     reput
    0.09
    riv
    0.09
    åįģä½Ļå¹´
    0.08
    è¾Ĺ转
    0.08
    åľ¨åIJĮä¸Ģ
    0.08
    约
    0.08
    æĻºåĬĽ
    0.08
    èģ²
    0.08
    Activations Density 0.052%

    No Known Activations