© 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. 1566
    Prev
    Next
    INDEX
    Explanations

    pose and poseable

    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
    ially
    -0.23
     haze
    -0.23
    usters
    -0.22
    ç±į
    -0.22
     cosa
    -0.22
    æİĮ声
    -0.20
    -handed
    -0.20
    ually
    -0.19
    çĦ¶æĺ¯
    -0.19
    åĤį
    -0.19
    POSITIVE LOGITS
    idon
    0.34
    holder
    0.24
    ä¸Ģå®ļçļĦ
    0.23
    holders
    0.22
    pone
    0.22
    ining
    0.20
    çĸijéĹ®
    0.20
    ftware
    0.19
    æ¦Ī
    0.19
    arks
    0.19
    Activations Density 0.019%

    No Known Activations