© 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. 1102
    Prev
    Next
    INDEX
    Explanations

    word origins

    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
    ulan
    -0.26
    _('
    -0.22
    icter
    -0.22
    anter
    -0.21
    bookmark
    -0.20
    checkpoint
    -0.20
    jh
    -0.20
     outr
    -0.20
    uhan
    -0.20
    ukes
    -0.20
    POSITIVE LOGITS
    means
    0.24
     Indicates
    0.23
    æĮĩ
    0.23
    æľī害
    0.23
     means
    0.22
    æ¼ĶåĮĸ
    0.22
     Consum
    0.22
    交æį¢
    0.22
    oted
    0.21
    Adj
    0.21
    Activations Density 0.042%

    No Known Activations