© 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. 18173
    Prev
    Next
    INDEX
    Explanations

    undergo conversion

    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
    IGN
    -0.09
    oven
    -0.09
    ç»ıæµİæĬĢæľ¯
    -0.08
     Fraud
    -0.08
    ign
    -0.08
    woo
    -0.08
    ignet
    -0.08
    绣çŃ¹æİ¨è¿Ľ
    -0.08
    é«»
    -0.08
    fonts
    -0.08
    POSITIVE LOGITS
    åıįå¼¹
    0.15
     bounce
    0.13
     bouncing
    0.12
     rico
    0.12
     bounced
    0.12
    æľĢ大ç¨ĭ度
    0.10
    	hit
    0.10
    èĿĻ
    0.09
    å¼¹æĢ§
    0.09
    åıįå°Ħ
    0.09
    Activations Density 0.042%

    No Known Activations