© 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. 16005
    Prev
    Next
    INDEX
    Explanations

    imgur.com links

    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
    è§ĩ
    -0.21
    ï¸
    -0.20
    pod
    -0.20
    clair
    -0.19
     Pods
    -0.19
    coverage
    -0.19
    樾
    -0.19
    uae
    -0.18
    ald
    -0.18
    atak
    -0.18
    POSITIVE LOGITS
    åĽ¾çīĩ
    0.22
    æĶ¾è¿ĩ
    0.21
    OTS
    0.21
    ä¸Ģå¼ł
    0.19
    .imgur
    0.19
    ä¸¤å¼ł
    0.19
    åĴĮåıijå±ķ
    0.18
    çĬĬ
    0.18
     img
    0.18
    urf
    0.18
    Activations Density 0.024%

    No Known Activations