© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36516
    Prev
    Next
    INDEX
    Explanations

    salvation and saved

    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
    etch
    -0.11
    åĻİ
    -0.10
     bitten
    -0.10
    abo
    -0.09
    强åĮĸ
    -0.09
    ings
    -0.09
    ETCH
    -0.09
    backs
    -0.09
    erver
    -0.09
    á»Ļng
    -0.09
    POSITIVE LOGITS
    åıijå±ķ空éĹ´
    0.10
    sports
    0.09
    ä¸Ńå¤ĸ
    0.09
    icina
    0.08
    baugh
    0.08
    à¸ķà¸Ļà¹Ģà¸Ńà¸ĩ
    0.08
    å·¥ä½ľä»»åĬ¡
    0.08
    åĸ¹
    0.08
    ä½ķå¤Ħ
    0.08
    éĢĶå¾Ħ
    0.08
    Activations Density 0.002%

    No Known Activations