© 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. 437
    Prev
    Next
    INDEX
    Explanations

    each of

    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
    xec
    -0.26
    å¤į
    -0.26
    æĿĤ
    -0.23
    Ptr
    -0.22
    def
    -0.22
    ä¸¥æł¼çļĦ
    -0.22
    ndef
    -0.21
    éĩı
    -0.21
     def
    -0.21
    è´Ł
    -0.21
    POSITIVE LOGITS
     respective
    0.26
    è¿Ļæī¹
    0.25
    /all
    0.25
     individual
    0.25
     offending
    0.25
    said
    0.24
     species
    0.24
    个åĪ«
    0.23
    .ContentType
    0.23
    avin
    0.23
    Activations Density 0.143%

    No Known Activations