© 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. 2911
    Prev
    Next
    INDEX
    Explanations

    U.S. Attorney

    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
    åıijå±ķä¸Ń
    -0.26
    okit
    -0.24
    outcome
    -0.24
    overlap
    -0.23
    idy
    -0.22
    ãĥĮ
    -0.22
    -New
    -0.22
    NCY
    -0.22
    opaque
    -0.22
    åĽ½å®¶æĪĺçķ¥
    -0.21
    POSITIVE LOGITS
    thon
    0.24
    otron
    0.23
    æ£į
    0.23
    å°Ĭ
    0.22
    ippi
    0.22
    åŀĤ
    0.22
    åĢĻéĢī人
    0.21
    /dc
    0.21
     Charles
    0.21
     Lines
    0.21
    Activations Density 0.048%

    No Known Activations