© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 316
    Prev
    Next
    INDEX
    Explanations

    eating a meal

    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¸Ģ个éĹ®é¢ĺ
    -0.22
    ream
    -0.20
     khÄĥn
    -0.20
    sj
    -0.20
    ä¸Ģ个éĩįè¦ģ
    -0.19
    ondo
    -0.19
    ä½Ĩä¸įéĻIJäºİ
    -0.19
    æĿ¯åŃIJ
    -0.18
    ausal
    -0.18
    ex
    -0.18
    POSITIVE LOGITS
    worm
    0.25
    ful
    0.24
    istic
    0.24
    itian
    0.23
    orative
    0.23
    èĤ´
    0.22
    wright
    0.22
    çĶ¨åĵģ
    0.22
    stead
    0.22
    stype
    0.21
    Activations Density 0.004%

    No Known Activations