© 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. 12504
    Prev
    Next
    INDEX
    Explanations

    Corbett or Corso

    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
    eger
    -0.22
    ellow
    -0.18
    scape
    -0.17
    enger
    -0.17
    rogen
    -0.17
    ¶
    -0.17
    egral
    -0.16
    elter
    -0.16
    aret
    -0.16
    ems
    -0.16
    POSITIVE LOGITS
    ridor
    0.19
    ally
    0.19
    æ¹ĥ
    0.19
    rado
    0.19
    说æĺ¯
    0.18
    æľ½
    0.18
    sey
    0.18
    deaux
    0.16
    Ľ
    0.16
    ìį¨
    0.16
    Activations Density 0.053%

    No Known Activations