© 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. 12758
    Prev
    Next
    INDEX
    Explanations

    modelproduct numbers or 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
     California
    -0.21
     minecraft
    -0.20
    æĸ½
    -0.20
     NYT
    -0.19
     Calif
    -0.19
    hest
    -0.19
    GitHub
    -0.19
     Chic
    -0.19
    California
    -0.18
    arte
    -0.18
    POSITIVE LOGITS
    åıijå±ķåīįæĻ¯
    0.21
    åķĨåĬ¡
    0.21
    è¿ĩ渡
    0.20
    usiness
    0.20
     erotisk
    0.20
    æĹĹèĪ°
    0.20
    yper
    0.19
    _based
    0.19
    å¯Ł
    0.19
    essaging
    0.19
    Activations Density 0.009%

    No Known Activations