© 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. 11007
    Prev
    Next
    INDEX
    Explanations

    notices or legal text headers

    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
    /is
    -0.18
    /w
    -0.18
    éĤ£ä»½
    -0.17
    hound
    -0.17
    æĤį
    -0.17
    friend
    -0.17
     prer
    -0.17
    hoe
    -0.17
    åļĨ
    -0.16
    hold
    -0.16
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.27
    ness
    0.23
    æľ½
    0.20
    nett
    0.20
    Ùij
    0.19
    ches
    0.18
    å¤ĩçĶ¨
    0.17
    nya
    0.17
    ional
    0.17
    é«ĵ
    0.17
    Activations Density 0.078%

    No Known Activations