© 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. 18547
    Prev
    Next
    INDEX
    Explanations

    thoughtful and intentional

    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
    å¾ģ
    -0.10
    æĴ¬
    -0.09
    没éĶĻ
    -0.09
    à¸Ħà¸Ń
    -0.08
    åŁ·
    -0.08
    vi
    -0.08
    ideo
    -0.08
    å®īæħ°
    -0.08
    UGE
    -0.08
    -console
    -0.08
    POSITIVE LOGITS
    æĢĿèĢĥ
    0.17
     thoughtful
    0.13
     thought
    0.12
    æĥ³äºĨ
    0.12
    thought
    0.12
    çļĦåħ³æ³¨
    0.11
    èĢĥãģĪãĤĭ
    0.11
    èĢĥãģĪ
    0.11
     thinking
    0.11
     Thought
    0.11
    Activations Density 0.043%

    No Known Activations