© 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. 13835
    Prev
    Next
    INDEX
    Explanations

    within messages

    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
    bullet
    -0.24
    que
    -0.19
    ou
    -0.19
     intr
    -0.19
     trailed
    -0.18
    Tuesday
    -0.18
    itä
    -0.18
    Ju
    -0.18
    omit
    -0.18
    Bullet
    -0.17
    POSITIVE LOGITS
    èĭįçĻ½
    0.22
     TestBed
    0.20
    å®ł
    0.20
    amba
    0.19
     ÐĴлад
    0.19
    éķĽ
    0.19
    /question
    0.18
    黯
    0.18
    åŀ¸
    0.18
    è¶ĬæĿ¥è¶Ĭå¤ļ
    0.18
    Activations Density 0.025%

    No Known Activations