© 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. 27060
    Prev
    Next
    INDEX
    Explanations

    adjectives for significance

    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
    çľĭèµ·æĿ¥
    -0.09
     ÑģÑĩиÑĤ
    -0.09
    ICAST
    -0.08
    å«ł
    -0.08
    iete
    -0.08
    å®ĥæĺ¯
    -0.08
    _opcode
    -0.08
    _REPLY
    -0.08
    sst
    -0.08
    venture
    -0.08
    POSITIVE LOGITS
    ä¹ĭ举
    0.09
    çªģçł´åı£
    0.09
    没æľīå¿ħè¦ģ
    0.09
    身å¤Ħ
    0.08
    èĩªèIJ¥
    0.08
    æľīå¿ħè¦ģ
    0.08
     ÙĪØ£ÙĨ
    0.08
    已达
    0.08
    ä¸įéĢĤ
    0.08
    ä¹ĭä½ľ
    0.08
    Activations Density 0.247%

    No Known Activations