© 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. 31098
    Prev
    Next
    INDEX
    Explanations

    outcomes and effects

    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
    å¸ľ
    -0.08
    çĶŁæŃ»
    -0.08
     interp
    -0.08
    à¹Ģà¸Ńà¸ģ
    -0.08
    ailable
    -0.08
    æݨèĸ¦
    -0.08
    æľīæīĢ
    -0.08
    .isRequired
    -0.08
    讼
    -0.08
    æ½®æµģ
    -0.08
    POSITIVE LOGITS
    åIJİæŀľ
    0.20
     consequences
    0.15
    åī¯ä½ľçĶ¨
    0.15
     effects
    0.14
    æķĪåºĶ
    0.13
    è´ŁéĿ¢å½±åĵį
    0.13
    æ·±è¿ľ
    0.12
    /effects
    0.12
     Effects
    0.12
    æķĪæŀľ
    0.12
    Activations Density 0.158%

    No Known Activations