© 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. 14260
    Prev
    Next
    INDEX
    Explanations

    thresholds, flow, position, blow

    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
     ÐĶм
    -0.22
    SupportedContent
    -0.22
    太å¤ļäºĨ
    -0.22
    PropertyParams
    -0.21
     ÐŁÐ¾Ñĩем
    -0.20
     wÅĽ
    -0.20
    SSIP
    -0.20
     ÐĶмиÑĤÑĢ
    -0.19
    راع
    -0.19
     pornost
    -0.19
    POSITIVE LOGITS
    æ¦
    0.21
    ç»®
    0.19
    emed
    0.19
    Sock
    0.19
    åĴİ
    0.18
    C
    0.18
    è¯Ģ
    0.18
    举è¡Į
    0.17
     sä
    0.17
     ther
    0.17
    Activations Density 0.276%

    No Known Activations