© 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. 1586
    Prev
    Next
    INDEX
    Explanations

    nick or nicki

    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
    CTOR
    -0.20
    -bodied
    -0.19
    evil
    -0.18
    ãģ¹ãģį
    -0.17
    aaaaaaaa
    -0.17
    Į
    -0.17
    ä¼Ļ
    -0.17
     Belly
    -0.16
    nda
    -0.16
    ç»ıåħ¸çļĦ
    -0.16
    POSITIVE LOGITS
    appa
    0.24
    nowledge
    0.23
    ories
    0.23
    olas
    0.23
    worthy
    0.23
    ened
    0.22
    olate
    0.22
    ×ķף
    0.22
    laus
    0.22
    able
    0.21
    Activations Density 0.031%

    No Known Activations