© 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. 16081
    Prev
    Next
    INDEX
    Explanations

    apr followed by 'ons' or 'on'

    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
    zelf
    -0.22
    ness
    -0.19
    erness
    -0.19
    NESS
    -0.18
    zik
    -0.17
    rub
    -0.17
    ãĤº
    -0.16
    ÑģпоÑĢ
    -0.15
    ers
    -0.15
    rain
    -0.15
    POSITIVE LOGITS
    ively
    0.22
    ðŁı»
    0.22
    ainted
    0.19
    rees
    0.18
    idge
    0.17
    cient
    0.17
    媳
    0.17
    olec
    0.16
    ucker
    0.16
    adio
    0.16
    Activations Density 0.008%

    No Known Activations