© 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. 1862
    Prev
    Next
    INDEX
    Explanations

    introductions and section headings

    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
    åIJĮæĹ¶ä¹Ł
    -0.23
    è¿Ļ个æĹ¶ä»£
    -0.23
    èī¯
    -0.23
    auses
    -0.22
    æĬ¢åħĪ
    -0.22
     MMI
    -0.22
    就好
    -0.21
    åľ¨éĩĮéĿ¢
    -0.21
    _QUOTES
    -0.20
    ç»ĻæĤ¨
    -0.20
    POSITIVE LOGITS
     Viol
    0.23
    oretical
    0.22
     Harm
    0.22
    éĢ¢
    0.22
    åŁºæľ¬æĥħåĨµ
    0.21
     proper
    0.20
     Enc
    0.20
     Prop
    0.20
     Begin
    0.20
     stroke
    0.20
    Activations Density 0.331%

    No Known Activations