© 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. 10813
    Prev
    Next
    INDEX
    Explanations

    at this point

    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
    åľ¨åĨħçļĦ
    -0.19
    SPAN
    -0.19
    er
    -0.18
    äºĨä¸Ģæī¹
    -0.18
    æĻ°
    -0.18
    çĶ¨äºİ
    -0.18
     oldest
    -0.17
    eros
    -0.17
    igy
    -0.17
    ĶåĽŀ
    -0.17
    POSITIVE LOGITS
     outset
    0.24
    æŶåĢĻ
    0.23
    temps
    0.23
     ÑĥÑĢовне
    0.22
    æŶéĹ´åĨħ
    0.22
    ç¼Ģ
    0.20
    éĺ¶æ®µ
    0.20
    OrDefault
    0.20
    æĻĤçĤ¹ãģ§
    0.19
    rophic
    0.19
    Activations Density 0.033%

    No Known Activations