© 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. 1855
    Prev
    Next
    INDEX
    Explanations

    performed / developed / employed

    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
     Beat
    -0.25
    Beat
    -0.25
    åħ¬çĶ¨
    -0.23
     Monter
    -0.23
     genders
    -0.21
    ä¹ĭæĺŁ
    -0.21
    beat
    -0.21
    ngo
    -0.21
    ceiver
    -0.20
     tem
    -0.20
    POSITIVE LOGITS
    çŃīåĽłç´ł
    0.24
    çŃī诸å¤ļ
    0.24
    çŃīåİŁåĽł
    0.23
    çŃīä¸Ģç³»åĪĹ
    0.23
    ç¥İ
    0.23
    对æİ¥
    0.22
    åĽĬ
    0.21
    ä½ľçĶ¨
    0.21
    employed
    0.21
    è¿Ļæł·çļĦè¯Ŀ
    0.21
    Activations Density 0.396%

    No Known Activations