© 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. 2974
    Prev
    Next
    INDEX
    Explanations

    skip something

    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
    ea
    -0.23
    icken
    -0.22
    ux
    -0.21
    ikes
    -0.21
    ead
    -0.20
    á»±c
    -0.20
    ifact
    -0.20
    ele
    -0.20
     ung
    -0.20
    uring
    -0.19
    POSITIVE LOGITS
    pered
    0.20
    ableObject
    0.20
    æİī
    0.20
    pler
    0.19
    çĦ¶
    0.19
    -proof
    0.19
    buster
    0.19
    æİīäºĨ
    0.19
    able
    0.18
    ij
    0.18
    Activations Density 0.028%

    No Known Activations