© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 1134
    Prev
    Next
    INDEX
    Explanations

    "AS IS" warranty disclaimer

    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
     /*----------------------------------------------------------------
    -0.25
    ä¹ŁæŃ£æĺ¯
    -0.25
     “
    -0.24
     «
    -0.23
     ware
    -0.22
    -related
    -0.22
    ä¹ŁåĽłæŃ¤
    -0.21
    “A
    -0.21
    —which
    -0.21
    说åΰè¿ĻéĩĮ
    -0.20
    POSITIVE LOGITS
    ä¸Ģ带ä¸Ģè·¯
    0.30
    åįģäºĮäºĶ
    0.29
    ()"
    0.28
    =="
    0.25
    æĪijè¦ģ
    0.25
    ï¼Ł”
    0.25
    []"
    0.24
    ?”
    0.24
    !”
    0.24
    ":č↵
    0.23
    Activations Density 0.817%

    No Known Activations