© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 862
    Prev
    Next
    INDEX
    Explanations

    XMLRPC calls and claims

    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
    èĿ¶
    -0.28
    åı£æ°Ķ
    -0.25
    CLU
    -0.25
    åĹĵåŃIJ
    -0.25
    èĪªçıŃ
    -0.25
     inhal
    -0.24
    aos
    -0.24
    longleftrightarrow
    -0.24
    éĽ¾éľ¾
    -0.24
    å·´é»İ
    -0.23
    POSITIVE LOGITS
     chip
    0.28
    ç²®
    0.28
     Ethiopia
    0.27
     Chips
    0.25
     Ethiopian
    0.25
    糧
    0.24
    èĪĤ
    0.24
     Ethi
    0.24
     Governor
    0.24
    éķ¢
    0.24
    Activations Density 0.108%

    No Known Activations