© 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. 11814
    Prev
    Next
    INDEX
    Explanations

    floor locations

    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
     Ñģебе
    -0.20
     Ñģобой
    -0.19
    å¹´éĻIJ
    -0.18
    ductor
    -0.18
    istic
    -0.18
    ä¹Ŀå·ŀ
    -0.17
    åľĥ
    -0.17
    æľ¬äºº
    -0.17
    们
    -0.17
    à¸ģา
    -0.17
    POSITIVE LOGITS
    -most
    0.22
    /front
    0.18
    pra
    0.18
    é¹Ĺ
    0.18
    æľīä¸Ģä½į
    0.17
    _ASCII
    0.17
    opens
    0.17
    åıĬ以ä¸Ĭ
    0.17
    atal
    0.16
    aming
    0.16
    Activations Density 0.009%

    No Known Activations