© 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. 6656
    Prev
    Next
    INDEX
    Explanations

    percentage and fold increases

    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
    spo
    -0.11
    Spo
    -0.10
     Spo
    -0.09
     spoiler
    -0.09
    ulls
    -0.08
    LES
    -0.08
    å§Ŀ
    -0.08
     spoilers
    -0.08
    çĿ«
    -0.08
    æĬ¤
    -0.08
    POSITIVE LOGITS
    åĢį
    0.18
    çĻ¾åĪĨä¹ĭ
    0.13
    åĬłåĢį
    0.12
    çĻ¾åĪĨçĻ¾
    0.11
    大å¹ħ度
    0.11
     gấp
    0.11
    å¢ŀéķ¿çİĩ
    0.10
    å¢ŀå¹ħ
    0.10
    涨å¹ħ
    0.10
     Dou
    0.09
    Activations Density 0.044%

    No Known Activations