© 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. 2397
    Prev
    Next
    INDEX
    Explanations

    CLAIM ENTS

    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
    è´§æºIJ
    -0.23
     ÐŁÐ¾Ñĩем
    -0.22
    elson
    -0.22
    æĽ´å¥½
    -0.22
    æŃ£åĵģ
    -0.21
     Omega
    -0.21
     ti
    -0.21
     ÐĶм
    -0.21
     rot
    -0.21
     ê
    -0.20
    POSITIVE LOGITS
     occasion
    0.26
     [('
    0.24
    abee
    0.24
    Listeners
    0.23
    EventListener
    0.23
    -browser
    0.23
    Explanation
    0.22
    忽çĦ¶
    0.22
    æºŁ
    0.21
    ropolis
    0.21
    Activations Density 0.232%

    No Known Activations