© 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. 13293
    Prev
    Next
    INDEX
    Explanations

    names ending with 'n'

    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
    ting
    -0.40
    TING
    -0.32
    ning
    -0.26
    ter
    -0.26
    zelf
    -0.25
    tera
    -0.24
    tern
    -0.23
    ningen
    -0.23
    åħĴ
    -0.23
    ging
    -0.22
    POSITIVE LOGITS
    eur
    0.28
    t
    0.28
    itude
    0.23
    ä¾¿å®ľ
    0.21
    eus
    0.20
    inator
    0.19
    otten
    0.19
    à¹Į
    0.19
    ibrary
    0.18
    ered
    0.18
    Activations Density 1.043%

    No Known Activations