© 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. 2395
    Prev
    Next
    INDEX
    Explanations

    skin tightening and elasticity

    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
     Bomb
    -0.24
    пиÑģан
    -0.24
    æħİ
    -0.23
    omit
    -0.23
    å¤ĩ
    -0.23
    çIJ³
    -0.22
     mex
    -0.22
     understanding
    -0.22
    å½ĵäºĭ
    -0.22
     Ink
    -0.22
    POSITIVE LOGITS
    æĶ¶ç´§
    0.37
    è¡°èĢģ
    0.31
    æĮĤéĴ©
    0.26
    èĢģé¾ĦåĮĸ
    0.26
    æµģ失
    0.25
    çļĦèĢģ
    0.24
    chw
    0.24
    ä¸ĭæ»ij
    0.24
    _Thread
    0.23
    æĶ¶ç¼©
    0.23
    Activations Density 0.014%

    No Known Activations