© 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. 16567
    Prev
    Next
    INDEX
    Explanations

    savage, primitive, wild, Conan

    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
    ¤í
    -0.18
    itive
    -0.17
    æĭĪ
    -0.17
    ainter
    -0.17
    shadow
    -0.17
    umber
    -0.17
    acie
    -0.17
    éĶ±
    -0.17
    edList
    -0.17
    æ°ijçĶŁ
    -0.17
    POSITIVE LOGITS
    0.27
    /exp
    0.17
    -looking
    0.17
     воÑĤ
    0.17
    rud
    0.17
    htag
    0.17
    -minded
    0.17
    éĩİ
    0.17
     cons
    0.16
     wild
    0.16
    Activations Density 0.005%

    No Known Activations