© 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. 62158
    Prev
    Next
    INDEX
    Explanations

    pieces, chunks, fragments

    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
    æ¸ħåĩī
    -0.09
    æĭį
    -0.08
    审
    -0.08
    çģ°
    -0.08
    è·ª
    -0.08
    oot
    -0.08
    èĢ½
    -0.08
    unused
    -0.08
    å±
    -0.08
    åŃķæľŁ
    -0.08
    POSITIVE LOGITS
    åĿĹ
    0.13
     fragments
    0.12
    å¡Ĭ
    0.12
    ç¢İ
    0.12
    ä¸ĢåĿĹ
    0.11
    åĪĨè¡Į
    0.11
    .newInstance
    0.11
     chunks
    0.11
    ç¢İçīĩ
    0.10
    çł´ç¢İ
    0.10
    Activations Density 0.084%

    No Known Activations