© 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. 590
    Prev
    Next
    INDEX
    Explanations

    of which

    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
    ÐķÐĿ
    -0.23
    CELER
    -0.22
     bothered
    -0.21
    åģıä½İ
    -0.21
     iota
    -0.21
    das
    -0.20
    åı¤èĢģçļĦ
    -0.20
    æĹħ游度åģĩ
    -0.20
    aida
    -0.20
     kicker
    -0.20
    POSITIVE LOGITS
     whose
    0.35
     which
    0.34
     коÑĤоÑĢÑĭÑħ
    0.33
     коÑĤоÑĢого
    0.31
    which
    0.30
     коÑĤоÑĢÑĭм
    0.30
     thereof
    0.29
     коÑĤоÑĢой
    0.29
     consisting
    0.28
     których
    0.28
    Activations Density 0.045%

    No Known Activations