© 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. 19375
    Prev
    Next
    INDEX
    Explanations

    would be / have

    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
    åIJ¦
    -0.12
    é¢Ħ计å°Ĩ
    -0.09
    OPY
    -0.09
    ä»»ä½ķ人
    -0.08
    å¥Ķè·ij
    -0.08
    imore
    -0.08
    ister
    -0.08
    IFA
    -0.08
    ping
    -0.08
    åħijæį¢
    -0.08
    POSITIVE LOGITS
    èĥ½å¤Ł
    0.21
    èĥ½å¤Łåľ¨
    0.21
    åı¯ä»¥åľ¨
    0.20
    åı¯ä»¥
    0.19
    èĥ½å¤ł
    0.19
    åı¯ä»¥éĢļè¿ĩ
    0.17
    ãģĵãģ¨ãģĮãģ§ãģįãģ¾ãģĻ
    0.17
    åı¯ä»¥ä»İ
    0.17
    å®ĥåı¯ä»¥
    0.17
    éĥ½èĥ½å¤Ł
    0.17
    Activations Density 0.517%

    No Known Activations