© 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. 5553
    Prev
    Next
    INDEX
    Explanations

    unauthorized access and actions

    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
    iqué
    -0.09
    鼷
    -0.09
    éĢĢåĽŀ
    -0.08
    çĶ³è¯·
    -0.08
    åĨł
    -0.08
    ÙħØ´
    -0.08
    åĪĩéĻ¤
    -0.08
    ä¸ĢåĪĻ
    -0.07
    äºĮ线
    -0.07
    åѤ
    -0.07
    POSITIVE LOGITS
    avar
    0.09
    çĶļèĩ³
    0.09
    éĴĵé±¼
    0.09
    uges
    0.09
    ç»Ĩ
    0.09
     вла
    0.09
    交æĺĵå¹³åı°
    0.09
    çķħ
    0.09
     Curtain
    0.08
    çªĥ
    0.08
    Activations Density 0.090%

    No Known Activations