© 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. 11318
    Prev
    Next
    INDEX
    Explanations

    horizontal separators

    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
    .Minimum
    -0.22
    çļĦæĸ°
    -0.20
    车åºĵ
    -0.20
    til
    -0.19
    upt
    -0.19
    å¥ĸ
    -0.19
    ogy
    -0.19
    æĩĤå¾Ĺ
    -0.19
    ah
    -0.19
    ç¯ĩ
    -0.18
    POSITIVE LOGITS
    CloseOperation
    0.23
    å®īåĢį
    0.22
    çļĤ
    0.21
    æīĵåIJ¬
    0.20
    _nr
    0.19
    åºĶçĶ¨æŁ¥çľĭ
    0.19
    ValueHandling
    0.19
     mdi
    0.19
    AccessType
    0.19
    _md
    0.18
    Activations Density 0.107%

    No Known Activations