© 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. 1590
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

    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
     rounded
    -0.25
    am
    -0.24
     ROT
    -0.24
     BF
    -0.23
    ~/
    -0.23
    irs
    -0.22
     code
    -0.22
    壹
    -0.22
     submenu
    -0.22
    DSA
    -0.21
    POSITIVE LOGITS
    ä¸įçĶ±
    0.24
    ött
    0.24
     nostalg
    0.23
    ä½Ĩå®ŀéĻħä¸Ĭ
    0.23
    UBE
    0.23
     Tradable
    0.23
    —but
    0.22
     discipl
    0.22
     Colomb
    0.22
    èĥĥåı£
    0.22
    Activations Density 0.822%

    No Known Activations