© 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. 12708
    Prev
    Next
    INDEX
    Explanations

    von followed by surname or "dissertation"

    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
    ly
    -0.19
    ÑĤÑĮ
    -0.18
    çĦ¶
    -0.18
    phone
    -0.17
    ustin
    -0.17
    ured
    -0.17
    tte
    -0.17
    ãģªãģı
    -0.16
    RICT
    -0.16
    tim
    -0.16
    POSITIVE LOGITS
    itive
    0.18
    å¾Ĺèµ·
    0.18
    soever
    0.17
    nis
    0.17
    /to
    0.17
    åŃĹæ¯į
    0.17
    -profit
    0.17
    /if
    0.16
    /from
    0.16
    nelly
    0.15
    Activations Density 0.057%

    No Known Activations