© 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. 23330
    Prev
    Next
    INDEX
    Explanations

    bumpy, hills, valleys, irregular surfaces

    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
    Messaging
    -0.10
    è±¹
    -0.09
    irez
    -0.09
    horn
    -0.09
    ä¿®æŃ£
    -0.09
    edition
    -0.08
     CUT
    -0.08
    íħľ
    -0.08
    ç²īç¢İ
    -0.08
    -component
    -0.08
    POSITIVE LOGITS
    èµ·ä¼ı
    0.12
    çĺ¤
    0.10
    å£ij
    0.10
     bump
    0.10
     Peaks
    0.10
     bumps
    0.10
    å³°
    0.10
    å³°ä¼ļ
    0.10
    累累
    0.09
    åľ°è²Į
    0.09
    Activations Density 0.156%

    No Known Activations