© 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. 2320
    Prev
    Next
    INDEX
    Explanations

    black suspects, Americans, teen, president, conservatives, Lives, guy, love

    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
    oret
    -0.23
    itel
    -0.22
    æķĪæŀľåĽ¾
    -0.22
    åĨľå®¶ä¹IJ
    -0.22
    ipse
    -0.21
    hey
    -0.21
    ä»ĭç»įä¸Ģä¸ĭ
    -0.20
    unset
    -0.20
    å·¾
    -0.20
     adjoining
    -0.20
    POSITIVE LOGITS
    -dominated
    0.31
    åIJĮèĥŀ
    0.26
    è£Ķ
    0.25
    为主çļĦ
    0.24
    -centric
    0.24
     subs
    0.24
    -owned
    0.24
    è§īéĨĴ
    0.23
    ischer
    0.23
    esen
    0.23
    Activations Density 0.015%

    No Known Activations