© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15097
    Prev
    Next
    INDEX
    Explanations

    king and army members

    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
    Łèĥ½
    -0.24
    ç¬ij
    -0.23
    ä»ĸå¦Ī
    -0.22
    á¿ij
    -0.22
    çĥ«
    -0.22
    åijĽ
    -0.20
    èĨĽ
    -0.20
    Ṫ
    -0.20
    椴
    -0.20
     ninete
    -0.20
    POSITIVE LOGITS
    Council
    0.21
    å®ļå±ħ
    0.21
    UAGE
    0.21
     Xperia
    0.21
    çļĦåľŁåľ°
    0.20
    erah
    0.20
    æį®è¯´
    0.20
    bote
    0.20
    vet
    0.20
    åºŁå¼ĥ
    0.20
    Activations Density 0.216%

    No Known Activations