© 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. 12854
    Prev
    Next
    INDEX
    Explanations

    ladies

    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
    ingly
    -0.20
    ible
    -0.19
    ément
    -0.18
    éĥ¨åī¯éĥ¨éķ¿
    -0.17
    ¤
    -0.16
     massive
    -0.16
    人寿
    -0.16
    ions
    -0.16
     noqa
    -0.15
    ylvania
    -0.15
    POSITIVE LOGITS
    hood
    0.26
    åĢij
    0.24
    们çļĦ
    0.24
    们
    0.19
    -made
    0.16
    hz
    0.16
    åĥļ
    0.16
     أعÙħاÙĦ
    0.16
    weight
    0.16
     Gaga
    0.15
    Activations Density 0.007%

    No Known Activations