© 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. 1345
    Prev
    Next
    INDEX
    Explanations

    CPU, disk, Point, Central, density, chain

    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
    DED
    -0.23
    !'↵
    -0.22
    åģĥ
    -0.21
    !';↵
    -0.21
    éĺı
    -0.21
    Verts
    -0.21
    	ADD
    -0.21
    追ãģĦ
    -0.20
    _FAIL
    -0.20
     cạnh
    -0.20
    POSITIVE LOGITS
    bai
    0.25
    æĬij
    0.22
    ixer
    0.22
    enz
    0.21
     nuisance
    0.21
    è¿Ļä½į
    0.21
     Petr
    0.21
    å¼ķ
    0.21
    å±Ĭ
    0.20
    çĿ¦
    0.20
    Activations Density 0.191%

    No Known Activations