© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51016
    Prev
    Next
    INDEX
    Explanations

    computing and internet technologies

    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
    çĥŁ
    -0.10
    Ñĩин
    -0.09
    eparator
    -0.09
    åī²
    -0.09
     Äijủ
    -0.08
    éĢĢ
    -0.08
     Cristiano
    -0.08
    indr
    -0.08
    .cz
    -0.08
    åıį对
    -0.08
    POSITIVE LOGITS
    æ³ĵ
    0.09
    è¿ŀèĥľ
    0.09
    æĮĩå°ĸ
    0.09
    mv
    0.08
    æ¯įåħ¬åı¸
    0.08
    解æĶ¾
    0.08
    èĺijèıĩ
    0.08
    -linked
    0.08
    å®Įç»ĵ
    0.08
    æĻ¯å¾·
    0.08
    Activations Density 0.423%

    No Known Activations