© 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. 11086
    Prev
    Next
    INDEX
    Explanations

    website and software terms

    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
    mapping
    -0.21
    Gold
    -0.21
    Mapping
    -0.20
    .Mapping
    -0.20
    ine
    -0.19
    è¿ĺæĺ¯å¾Ī
    -0.19
    GR
    -0.19
     Gold
    -0.18
    er
    -0.18
     mapping
    -0.18
    POSITIVE LOGITS
    åıĬ缸åħ³
    0.23
    æ¼±
    0.22
    åıĬåħ¶
    0.21
    轻微
    0.21
    以åıĬåħ¶ä»ĸ
    0.19
    ä¸Ĭå¹´
    0.19
    ÑģÑħ
    0.19
    senal
    0.19
    å´§
    0.18
    andon
    0.18
    Activations Density 0.025%

    No Known Activations