© 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. 1340
    Prev
    Next
    INDEX
    Explanations

    pass to scorer

    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
    ÑĢажа
    -0.25
    ников
    -0.24
    equip
    -0.23
    å½»
    -0.22
    çīµ
    -0.22
    äºĶ个
    -0.22
    [attr
    -0.22
     mont
    -0.22
    康
    -0.21
    ç©¿æĪ´
    -0.21
    POSITIVE LOGITS
    è¿ĽçIJĥ
    0.28
     angled
    0.27
    èĮ¸
    0.26
     shot
    0.24
     crud
    0.24
    .easy
    0.24
    éļıæīĭ
    0.24
    娴
    0.24
    straight
    0.23
    æĭį
    0.23
    Activations Density 0.005%

    No Known Activations