© 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. 30084
    Prev
    Next
    INDEX
    Explanations

    licensed under the Apache License

    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
    etsk
    -0.09
    Ñħи
    -0.08
    æ¹į
    -0.08
    åIJİåĭ¤
    -0.08
    çī¢
    -0.08
    å®ľ
    -0.08
    丧失
    -0.08
    身穿
    -0.08
    è§ģè¿ĩ
    -0.08
    etically
    -0.08
    POSITIVE LOGITS
    ç¹ĩ
    0.11
    éĺ²åį«
    0.09
    ä½İ声
    0.09
    ampler
    0.09
    åıĪ好
    0.09
    çļĦä¸Ģåijĺ
    0.09
    åĩ±
    0.09
    æŀķ
    0.09
    .Skin
    0.08
    rone
    0.08
    Activations Density 0.002%

    No Known Activations