© 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. 38953
    Prev
    Next
    INDEX
    Explanations

    changes being made or occurring

    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
    ä¸ĢéĿ¢
    -0.10
     ëĶ°
    -0.10
    å²³
    -0.09
    esti
    -0.09
    ä¸Ģ头
    -0.09
    uity
    -0.09
    itting
    -0.09
    åİŁæłĩé¢ĺ
    -0.09
    æ¬ł
    -0.08
    _residual
    -0.08
    POSITIVE LOGITS
    å¹ħ度
    0.17
    åıijçĶŁåľ¨
    0.13
     changes
    0.12
    (changes
    0.12
    åıĺéĿ©
    0.11
    changes
    0.10
    太快
    0.10
     изменениÑı
    0.10
    åī§çĥĪ
    0.10
     happening
    0.10
    Activations Density 0.360%

    No Known Activations