© 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. 11324
    Prev
    Next
    INDEX
    Explanations

    syndrome or specific conditions

    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
    cope
    -0.22
    minus
    -0.19
    åīª
    -0.18
    dam
    -0.17
    _fatal
    -0.17
    åĨ¤
    -0.17
    åħĥæŦ
    -0.17
    åħįè´£
    -0.17
    CDATA
    -0.17
    DTD
    -0.17
    POSITIVE LOGITS
    æĿ¥çĶµ
    0.21
    OLDER
    0.20
    以èī²
    0.19
    è¿Ī
    0.18
    idend
    0.18
    渤
    0.18
    声
    0.17
    _constructor
    0.17
    anna
    0.17
    ipple
    0.17
    Activations Density 0.003%

    No Known Activations