© 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. 2327
    Prev
    Next
    INDEX
    Explanations

    parenthetical explanations

    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
    _ground
    -0.22
    çĶ¨éĢĶ
    -0.22
    æ§ģ
    -0.21
    _centers
    -0.21
    /grpc
    -0.21
    .slim
    -0.20
    éĥĬ
    -0.20
     Presence
    -0.20
    prep
    -0.20
    å¾ģç¨ĭ
    -0.20
    POSITIVE LOGITS
     irony
    0.32
    .)↵↵
    0.30
    .]↵↵
    0.27
     earlier
    0.26
    !).↵↵
    0.25
     ).↵↵
    0.24
     mistakenly
    0.24
    .)↵
    0.24
     apologies
    0.24
    quina
    0.24
    Activations Density 0.089%

    No Known Activations