© 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. 1689
    Prev
    Next
    INDEX
    Explanations

    Plaintiff, Jr, Trustee, Regional

    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
    åĸĬ
    -0.25
    è±Į
    -0.25
    min
    -0.24
    æ²»å®ī
    -0.24
    ince
    -0.22
     labeled
    -0.21
    (n
    -0.21
     noise
    -0.21
    _noise
    -0.21
    ges
    -0.20
    POSITIVE LOGITS
    /span
    0.23
    请çĤ¹åĩ»
    0.23
    esor
    0.23
     DEAL
    0.22
     Valid
    0.21
    _STRUCT
    0.21
     taper
    0.21
    EIF
    0.21
    ofil
    0.21
     vbox
    0.21
    Activations Density 0.125%

    No Known Activations