© 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. 13971
    Prev
    Next
    INDEX
    Explanations

    Crime Stoppers, Q:, Anonymous

    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
    ifest
    -0.21
    è®®äºĭ
    -0.21
    WithType
    -0.20
    æĶ¶å®ĺ
    -0.20
    绣é¢Ĩ
    -0.19
    çijķ
    -0.19
    &m
    -0.18
    ukes
    -0.18
    æīĵåĮħ
    -0.18
    å¸ļ
    -0.18
    POSITIVE LOGITS
    åĮ¿åIJį
    0.24
     Tin
    0.20
    CADE
    0.19
    åĪ©åĻ¨
    0.19
     anonymous
    0.19
    ecret
    0.18
    scribe
    0.18
    æ¯Ĵ
    0.18
    éķ¿æķĪ
    0.18
     Anonymous
    0.18
    Activations Density 0.002%

    No Known Activations