© 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. 16881
    Prev
    Next
    INDEX
    Explanations

    Gale, Marilyn, Gail

    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
    ðŁı»
    -0.20
    ptime
    -0.18
    ickle
    -0.18
    ðŁı¼
    -0.17
    upon
    -0.17
    ðŁı¾
    -0.16
    -Ta
    -0.16
     Dw
    -0.16
    ðŁı½
    -0.16
    ermen
    -0.16
    POSITIVE LOGITS
    aise
    0.17
    çĦ¶æĺ¯
    0.17
    ķ
    0.16
    Unhandled
    0.16
    ÑĦеÑģÑģ
    0.15
    inated
    0.15
    otas
    0.15
    sms
    0.15
     обÑĬ
    0.15
    ÑĢова
    0.15
    Activations Density 0.006%

    No Known Activations