© 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. 677
    Prev
    Next
    INDEX
    Explanations

    .json and platforms

    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
    AGR
    -0.24
    oppel
    -0.22
    æĮ½
    -0.22
     Natal
    -0.22
    稼
    -0.21
    ilon
    -0.20
    @student
    -0.20
     Reached
    -0.20
     Dag
    -0.20
     Ref
    -0.20
    POSITIVE LOGITS
    æĦıè§ģåıįé¦Ī
    0.22
     analy
    0.20
    ysis
    0.20
    çĽ¸å¹²
    0.20
    BERT
    0.20
    TECT
    0.20
    _elt
    0.20
    related
    0.20
    并åIJij
    0.20
    社ä¼ļæķĪçĽĬ
    0.20
    Activations Density 1.015%

    No Known Activations