© 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
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1414
    Prev
    Next
    INDEX
    Explanations

    configuration file parameters

    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
    oad
    -0.24
    FieldType
    -0.23
     **)&
    -0.22
    å°±ä¸įä¼ļ
    -0.22
    JsonObject
    -0.22
     McGu
    -0.22
    _FT
    -0.21
    å±±åºĦ
    -0.21
    athon
    -0.21
     entityId
    -0.21
    POSITIVE LOGITS
    ä½į
    0.27
    伤
    0.24
     frase
    0.23
    æ°Ķ
    0.23
    .capitalize
    0.23
    ä¸įæĪIJ
    0.23
    夫
    0.22
    éĹ®é¢ĺ
    0.22
    妻
    0.22
    /copyleft
    0.21
    Activations Density 0.809%

    No Known Activations