© 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. 1374
    Prev
    Next
    INDEX
    Explanations

    granny, Jackie, skinny, granddaughter

    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
    antis
    -0.23
    çĭİ
    -0.22
    gran
    -0.21
    ¸
    -0.20
    æĤłä¹ħ
    -0.19
    capacity
    -0.19
    gew
    -0.19
    ted
    -0.19
    è§Ĥ念
    -0.19
    disable
    -0.18
    POSITIVE LOGITS
    æĪ®
    0.21
     minded
    0.21
    erer
    0.21
     damn
    0.21
    èĢĮæĿ¥
    0.20
     lint
    0.20
    oring
    0.20
    ä¸Ģæľ¬ä¹¦
    0.19
    ï¸
    0.19
    laus
    0.19
    Activations Density 0.002%

    No Known Activations