© 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. 1955
    Prev
    Next
    INDEX
    Explanations

    uous, view, illustrations

    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
    amel
    -0.23
    edly
    -0.23
    ä¸Ģ个éĩįè¦ģ
    -0.23
    -upper
    -0.21
    NEY
    -0.20
    aic
    -0.20
    sip
    -0.20
    aday
    -0.20
    å°ıå¾®
    -0.20
    çī¹æ®ĬæĥħåĨµ
    -0.19
    POSITIVE LOGITS
     halls
    0.24
    uous
    0.24
    еÑģÑĤв
    0.23
     illustrations
    0.23
    åĴĮæľįåĬ¡
    0.23
    tx
    0.23
     hall
    0.23
    毳
    0.22
    ŀ
    0.21
     beasts
    0.21
    Activations Density 0.005%

    No Known Activations