© 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. 2528
    Prev
    Next
    INDEX
    Explanations

    stuffing or stuffed

    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
    IBUT
    -0.23
    ubo
    -0.21
    ocities
    -0.20
     rug
    -0.20
     Stam
    -0.20
    ä¹Ŀåįģ
    -0.19
     spotting
    -0.19
    溯
    -0.19
    踪
    -0.19
    adro
    -0.19
    POSITIVE LOGITS
    pile
    0.23
    è¢ĭ
    0.23
    sdale
    0.23
    alls
    0.22
    mates
    0.22
    town
    0.22
    hen
    0.20
    mate
    0.20
    æ··ä¹±
    0.20
     sacks
    0.20
    Activations Density 0.010%

    No Known Activations