© 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. 12052
    Prev
    Next
    INDEX
    Explanations

    pay for

    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
    igel
    -0.20
    ely
    -0.18
    rose
    -0.18
     Gentle
    -0.17
    .localized
    -0.17
    ROUT
    -0.17
     Household
    -0.17
    ilet
    -0.17
    åĪĨéĴŁå·¦åı³
    -0.17
    öl
    -0.17
    POSITIVE LOGITS
    è¿Ļä¸ĢåĪĩ
    0.21
    æĺĤè´µ
    0.21
    ä¸įæĿ¥
    0.20
    èĩªå·±åĸľæ¬¢
    0.20
    涩
    0.19
    å±ŀäºİèĩªå·±
    0.19
    éĻī
    0.19
     Ñģебе
    0.18
    累累
    0.18
    BUR
    0.18
    Activations Density 0.008%

    No Known Activations