© 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. 1804
    Prev
    Next
    INDEX
    Explanations

    skin-tight garments

    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
     canned
    -0.24
     Gulf
    -0.23
     vic
    -0.23
    Plain
    -0.22
    msp
    -0.22
     Islands
    -0.22
    NonNull
    -0.21
    æ·¹
    -0.21
     Nobel
    -0.21
    å²Ľå±¿
    -0.21
    POSITIVE LOGITS
    çijľä¼½
    0.31
    /stretch
    0.31
    -esque
    0.30
    -covered
    0.28
    å¼¹æĢ§
    0.26
    /autoload
    0.26
    èĪŀè¹Ī
    0.25
     fibre
    0.25
    åģ¥èº«
    0.25
    åľ°éģĵ
    0.24
    Activations Density 0.002%

    No Known Activations