© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13153
    Prev
    Next
    INDEX
    Explanations

    scalp or scalar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
     phẩm
    -0.18
    ãģıãĤĮ
    -0.17
    fried
    -0.16
    spr
    -0.16
    ãģĬãģı
    -0.16
    ราà¸Ĭà¸ģาร
    -0.15
    tube
    -0.15
    tap
    -0.15
    /on
    -0.15
    vid
    -0.15
    POSITIVE LOGITS
    erin
    0.21
    å±ij
    0.19
    itch
    0.17
    aber
    0.16
    ered
    0.15
    ÑĮÑı
    0.15
    à¹Į
    0.15
    亨
    0.15
    lesh
    0.15
    ize
    0.15
    Activations Density 0.007%

    No Known Activations