© 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. 1567
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ov
    -0.28
    roys
    -0.24
    éĢļçĶ¨
    -0.23
    çĶ¸
    -0.23
    mit
    -0.22
    è·¯
    -0.22
    arse
    -0.22
     rank
    -0.22
    代çIJĨ
    -0.22
     Synd
    -0.21
    POSITIVE LOGITS
     Funeral
    0.27
     funeral
    0.25
    殡
    0.25
    ä¸ĢåĪĻ
    0.24
    ç¥ł
    0.24
    SPEC
    0.23
    noise
    0.23
    woo
    0.23
     Shr
    0.23
     sincerely
    0.23
    Activations Density 0.000%

    No Known Activations