© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2749
    Prev
    Next
    INDEX
    Explanations

    Jose and hose names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    ãģĵãģ¨
    -0.28
    å±ij
    -0.25
    ä¸įäºĨ
    -0.22
    ãĤĤãģ®
    -0.21
    ective
    -0.20
     minded
    -0.20
    HING
    -0.20
    ect
    -0.20
    å¯Įè´µ
    -0.19
    ridge
    -0.19
    POSITIVE LOGITS
    idar
    0.23
    presso
    0.22
    phere
    0.21
    quet
    0.21
    BEGIN
    0.20
    	↵	↵	↵
    0.20
    prep
    0.20
    patial
    0.20
    fullname
    0.19
    inho
    0.19
    Activations Density 0.006%

    No Known Activations