© 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. 15471
    Prev
    Next
    INDEX
    Explanations

    questions and wonder

    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
    çºłæŃ£
    -0.19
    ivet
    -0.19
    æĮĩ示
    -0.18
    大æ¦Ĥ
    -0.18
    æī¹ç¤º
    -0.18
    æīĭ段
    -0.18
    çģµæĦŁ
    -0.18
    defer
    -0.18
    apol
    -0.18
    åľ°è²Į
    -0.17
    POSITIVE LOGITS
     questions
    0.27
     wondered
    0.26
    çĸijéĹ®
    0.25
    ä¸Ģ个éĹ®é¢ĺ
    0.25
     wondering
    0.24
     Questions
    0.23
    Questions
    0.23
     wonder
    0.23
     whether
    0.21
    èĻij
    0.21
    Activations Density 0.037%

    No Known Activations