© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2299
    Prev
    Next
    INDEX
    Explanations

    parenthetical statements

    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
    段
    -0.23
    ENDOR
    -0.22
     POD
    -0.22
    ä¹ĭç¾İ
    -0.22
    aires
    -0.21
     himself
    -0.21
    izes
    -0.21
    isti
    -0.21
    i
    -0.20
    orig
    -0.20
    POSITIVE LOGITS
    ngle
    0.24
     singly
    0.22
     pure
    0.21
    yles
    0.21
     un
    0.21
    èħ¥
    0.20
    ussen
    0.20
    lte
    0.20
    lander
    0.20
    inqu
    0.20
    Activations Density 0.005%

    No Known Activations