© 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. 2507
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
    对èĩªå·±
    -0.27
    Nearly
    -0.24
    ofire
    -0.23
     Candle
    -0.23
    为空
    -0.23
    çĶ¸
    -0.23
    olec
    -0.22
    éĻª
    -0.22
     Nearly
    -0.21
    èĭ±æł¼
    -0.21
    POSITIVE LOGITS
     regulator
    0.28
    éĢ¸
    0.26
    çĽij管éĥ¨éŨ
    0.22
     regulators
    0.21
    éĺħ
    0.21
    erea
    0.21
     iterations
    0.20
    nos
    0.20
    ATEST
    0.20
     corporation
    0.20
    Activations Density 0.119%

    No Known Activations