© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1582
    Prev
    Next
    INDEX
    Explanations

    sensitive information and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     Hairst
    -0.27
    prit
    -0.25
    (Output
    -0.25
    迫使
    -0.24
    åıĺéĢŁ
    -0.24
    æķĪåºĶ
    -0.24
    å«ģ
    -0.23
    åĿĩåĮĢ
    -0.23
     Cousins
    -0.23
     contempor
    -0.23
    POSITIVE LOGITS
    åį±éĻ©
    0.49
    å®īåħ¨
    0.43
     sensitive
    0.43
     dangerous
    0.42
    çļĦå®īåħ¨
    0.42
    åį±éļª
    0.42
     unsafe
    0.41
     safety
    0.41
    å®īåħ¨ç®¡çIJĨ
    0.40
    æķıæĦŁ
    0.40
    Activations Density 0.226%

    No Known Activations