© 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. 1579
    Prev
    Next
    INDEX
    Explanations

    old or former relationships/roles

    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
     currently
    -0.30
     presently
    -0.29
     Currently
    -0.29
    icorn
    -0.28
    第ä¸ī代
    -0.25
    åĽ½å®¶æĪĺçķ¥
    -0.24
    å²ģ以ä¸Ĭ
    -0.24
    NESS
    -0.24
    å¹´æľ«
    -0.24
     ultimately
    -0.23
    POSITIVE LOGITS
    æŧ
    0.27
     знак
    0.26
    å·¥ä½ľçļĦ
    0.24
    èĪĬ
    0.24
    ures
    0.23
     selves
    0.23
    parent
    0.23
    为åħ¶
    0.22
    åIJĪä½ľä¼Ļä¼´
    0.22
    ç¥
    0.22
    Activations Density 0.019%

    No Known Activations