© 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. 16492
    Prev
    Next
    INDEX
    Explanations

    one of several

    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
    åıī
    -0.22
    æī¯
    -0.20
    ers
    -0.19
    éĥ¢
    -0.19
    ALS
    -0.18
    é£ŀè·ĥ
    -0.18
    çĪµå£«
    -0.18
    çĶ³
    -0.18
    umble
    -0.18
    oser
    -0.18
    POSITIVE LOGITS
    ä¼Ĺå¤ļ
    0.26
    诸å¤ļ
    0.22
     many
    0.21
    å°ijæķ°
    0.20
    许å¤ļ
    0.20
    許å¤ļ
    0.20
    many
    0.20
    among
    0.20
     several
    0.19
    ä¸įå½±åĵį
    0.19
    Activations Density 0.056%

    No Known Activations