© 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. 1552
    Prev
    Next
    INDEX
    Explanations

    UNPUBLISHED UNITED STATES COURT OF APPEALS

    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
    èĩ³å°Ĭ
    -0.25
     Malcolm
    -0.24
    é£İæĻ¯
    -0.23
    ãģŀ
    -0.23
     Curtain
    -0.23
    solution
    -0.23
     gravy
    -0.22
    _define
    -0.22
     Vanity
    -0.22
    _adj
    -0.21
    POSITIVE LOGITS
    å¤ĩ
    0.23
    çļĭ
    0.21
    ãĤĬ
    0.21
    esan
    0.21
     khảo
    0.21
     distressed
    0.21
    ENTS
    0.20
    inker
    0.20
    Classification
    0.20
    æĢ«
    0.20
    Activations Density 0.018%

    No Known Activations