© 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. 14642
    Prev
    Next
    INDEX
    Explanations

    BSD-style license

    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
    Ń
    -0.19
    abouts
    -0.19
    atics
    -0.19
    bert
    -0.18
    appropri
    -0.18
    most
    -0.17
    BB
    -0.17
     bÃłi
    -0.17
    rene
    -0.17
    å®ĿçŁ³
    -0.16
    POSITIVE LOGITS
    jamin
    0.27
     nhiêu
    0.24
    ruptcy
    0.23
    iful
    0.22
     Isles
    0.22
    camp
    0.21
    deaux
    0.20
    antine
    0.20
    irectional
    0.20
    å¨ĺ
    0.19
    Activations Density 3.519%

    No Known Activations