© 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. 11994
    Prev
    Next
    INDEX
    Explanations

    percentages and counts

    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
    第ä¸Ģ次
    -0.21
     ones
    -0.21
    ember
    -0.20
    çł´
    -0.19
     Herz
    -0.19
     Wag
    -0.19
     Inspir
    -0.17
    çĻ½éĵ¶
    -0.17
    æĬĺ
    -0.17
    ErrorException
    -0.17
    POSITIVE LOGITS
    æĿµ
    0.24
    ç»ĨåĪĨ
    0.23
    å¹²èĦĨ
    0.23
    沩
    0.20
    ç°ª
    0.18
    缴è¾ĸ
    0.18
    éĹ®æĪij
    0.18
    è¦ĨçĽĸ
    0.18
    åĹħ
    0.18
    vrier
    0.18
    Activations Density 0.015%

    No Known Activations