© 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. 1779
    Prev
    Next
    INDEX
    Explanations

    versions of series

    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
    ä¸ĢéĹ´
    -0.27
    å®ıè§Ĥ
    -0.24
     SUBSTITUTE
    -0.24
    æł²
    -0.24
    quare
    -0.23
     eher
    -0.23
    éĹ´éļĻ
    -0.23
    RLF
    -0.23
    oust
    -0.22
     Closet
    -0.22
    POSITIVE LOGITS
    æIJŃè½½
    0.36
    ãĤ·ãĥªãĥ¼ãĤº
    0.32
    -Series
    0.31
     versions
    0.30
    -series
    0.30
    çĶ¨æĪ·æıIJä¾Ľ
    0.29
    anium
    0.28
    éħįå¤ĩäºĨ
    0.28
     series
    0.27
    (version
    0.27
    Activations Density 0.095%

    No Known Activations