© 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. 2490
    Prev
    Next
    INDEX
    Explanations

    image, photo, file

    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
    æķ£
    -0.25
    ndo
    -0.23
    -du
    -0.23
    çļĦéģĵçIJĨ
    -0.21
    _Parms
    -0.21
    agina
    -0.21
    ynchronize
    -0.21
    odos
    -0.21
    åIJĮåŁİ
    -0.20
    è¾Ľèĭ¦
    -0.20
    POSITIVE LOGITS
    _IMG
    0.28
    çħ§çīĩ
    0.26
     images
    0.26
    åĽ¾åĥı
    0.26
    images
    0.25
    åĽ¾çīĩ
    0.25
     photos
    0.25
    ä¾ĽåĽ¾
    0.24
    åIJijè®°èĢħ
    0.24
     imgs
    0.24
    Activations Density 0.046%

    No Known Activations