© 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. 11162
    Prev
    Next
    INDEX
    Explanations

    connecting clauses or lists

    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
    erview
    -0.23
    	RTLR
    -0.20
    èĽ¸
    -0.20
    .ObjectModel
    -0.20
    @student
    -0.20
    incess
    -0.19
    .mx
    -0.19
    ommen
    -0.19
    esen
    -0.19
    èĽĻ
    -0.19
    POSITIVE LOGITS
    å°ij许
    0.22
    使ä¹ĭ
    0.21
    ä¸Ģèµ·
    0.20
    åı¦ä¸Ģè¾¹
    0.20
    çļĩåŃIJ
    0.19
    使å¾Ĺ
    0.19
    nom
    0.19
    çĦ¶åIJİ
    0.19
    ç«ĭåį³
    0.19
    èĩ³åħ³
    0.18
    Activations Density 0.014%

    No Known Activations