© 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. 15503
    Prev
    Next
    INDEX
    Explanations

    Valentine and related names

    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
    ../../../
    -0.19
    (crate
    -0.18
    science
    -0.17
    èħ±
    -0.17
    ол
    -0.17
    ç¥ĩ
    -0.16
    ../../
    -0.16
    ness
    -0.16
    edList
    -0.15
    åīįæīĢ
    -0.15
    POSITIVE LOGITS
    ãģĤãĤĭ
    0.17
    ÑģÑĮ
    0.16
    ãģ³
    0.16
    court
    0.16
    mma
    0.15
    ized
    0.15
    yu
    0.15
    arily
    0.15
    how
    0.15
    UDA
    0.15
    Activations Density 0.007%

    No Known Activations