© 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. 2930
    Prev
    Next
    INDEX
    Explanations

    downright/outright + negative descriptor

    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
    ãģĨãģ¡ãģ«
    -0.26
    ÑĩÑĢежден
    -0.25
    åı£æ°Ķ
    -0.24
    ä¸Ģéģĵ
    -0.24
     accordingly
    -0.23
    缴è§Ĥ
    -0.23
    ials
    -0.23
    çĽ´è¾¾
    -0.23
    ä¹ŁåIJĮæł·
    -0.22
    /w
    -0.22
    POSITIVE LOGITS
     refuse
    0.24
    åıĽ
    0.23
     refuses
    0.23
    deb
    0.22
    dehyde
    0.21
    æĪij以为
    0.21
    tutorial
    0.21
     prejudice
    0.21
    åı¯ä»¥è¯´
    0.21
     prohib
    0.20
    Activations Density 0.007%

    No Known Activations