© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1404
    Prev
    Next
    INDEX
    Explanations

    in your face

    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
    éĻ¤å¤ĸ
    -0.24
    nds
    -0.24
    CRET
    -0.23
     Wig
    -0.23
    骥
    -0.23
    åĩºæ¸¸
    -0.22
     santa
    -0.22
    iper
    -0.22
    ä»ĸèĩªå·±
    -0.22
    Santa
    -0.21
    POSITIVE LOGITS
    éĿ¢åīį
    0.28
     forcefully
    0.25
     immedi
    0.24
    ä¸Ģ大åłĨ
    0.23
     constantly
    0.23
    åĴĦ
    0.22
     aggressively
    0.22
    èĢ³è¾¹
    0.22
    åĴ«
    0.21
     confronted
    0.21
    Activations Density 0.016%

    No Known Activations