© 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. 14189
    Prev
    Next
    INDEX
    Explanations

    street name or location

    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
    举äºļ
    -0.23
    éĽ¾
    -0.19
    partment
    -0.18
    Å¡t
    -0.18
    estatus
    -0.18
    æĪ¾
    -0.18
    å¹ķåIJİ
    -0.18
     Bark
    -0.17
    psc
    -0.17
    æ¡¢
    -0.17
    POSITIVE LOGITS
    íĶ¼
    0.21
    åĿĩè¡¡
    0.19
     DNC
    0.19
    èĥª
    0.18
    è®©ä½ł
    0.18
    åĪĨåħ¬åı¸
    0.18
    æī¬
    0.17
     evidently
    0.17
    digest
    0.17
     наÑĢ
    0.17
    Activations Density 0.001%

    No Known Activations