© 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. 53259
    Prev
    Next
    INDEX
    Explanations

    maximum period or length

    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
    çĢij
    -0.10
    rant
    -0.10
     desn
    -0.10
    åijĬè¯īä½ł
    -0.09
    outu
    -0.08
    ution
    -0.08
    æĭ³
    -0.08
    راء
    -0.08
    å¾ģ
    -0.08
    ä¹ĸä¹ĸ
    -0.08
    POSITIVE LOGITS
    ä¸įè¶ħè¿ĩ
    0.13
    潦
    0.11
    ä¹Łä¸įè¦ģ
    0.10
    èĻ¬
    0.10
    ä¸Ģå®ļæĺ¯
    0.09
    ãĥĨãĥ¼ãĥŀ
    0.09
    两人
    0.09
    IMUM
    0.09
    éºĿ
    0.09
    åģ°
    0.09
    Activations Density 0.031%

    No Known Activations