© 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. 13772
    Prev
    Next
    INDEX
    Explanations

    chunking or size of chunks

    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
     handjob
    -0.16
    .annotate
    -0.15
    æĥ³è±¡åĬĽ
    -0.15
    èĬ±å¼Ģ
    -0.15
    eut
    -0.15
    çļ¿
    -0.15
    å¾Ĵ
    -0.14
    venge
    -0.14
    encing
    -0.14
     phẩm
    -0.14
    POSITIVE LOGITS
    åĦ¿
    0.30
    åĿĹ
    0.22
    sets
    0.21
    åħĴ
    0.21
    size
    0.20
    lets
    0.20
    mates
    0.20
    astic
    0.20
    ified
    0.19
    ย
    0.19
    Activations Density 0.016%

    No Known Activations