© 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. 12168
    Prev
    Next
    INDEX
    Explanations

    photograph

    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
    -0.24
    hift
    -0.23
    hower
    -0.16
    ĭ
    -0.15
    amer
    -0.15
    hattan
    -0.15
    èĩªåĪ¶
    -0.15
    wear
    -0.15
    chaft
    -0.15
    pir
    -0.14
    POSITIVE LOGITS
    /video
    0.24
    hoot
    0.20
    matic
    0.19
    ically
    0.19
    /videos
    0.17
    ological
    0.17
    /photo
    0.16
    é¹Ĥ
    0.16
    soever
    0.16
    oral
    0.16
    Activations Density 0.093%

    No Known Activations