© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 56
    Prev
    Next
    INDEX
    Explanations

    #define clauses

    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
     AudioSource
    -0.24
    indle
    -0.24
     Enumerator
    -0.22
    WF
    -0.22
     ENUM
    -0.22
    æĸ°éĽ¶åĶ®
    -0.21
    TypeEnum
    -0.21
     females
    -0.21
    Enumerable
    -0.21
    _validation
    -0.21
    POSITIVE LOGITS
    fixtures
    0.27
    书记
    0.25
    /fixtures
    0.25
    å±ĭéĩĮ
    0.25
    ved
    0.24
    ä»İä¸Ń
    0.24
     derecho
    0.23
    å¹³æĸ¹
    0.22
    éģĵçIJĨ
    0.22
     nested
    0.21
    Activations Density 0.003%

    No Known Activations