© 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. 2877
    Prev
    Next
    INDEX
    Explanations

    access to post

    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
    主导
    -0.26
    渥
    -0.26
    åĪĿ
    -0.25
     dominate
    -0.24
    ç»Ī身
    -0.24
    绣ä¸Ģ
    -0.24
     domin
    -0.24
    arna
    -0.24
     schemes
    -0.23
    ernen
    -0.23
    POSITIVE LOGITS
    åģļä¸ĢäºĽ
    0.26
    å¾Īå¤ļäºĭæĥħ
    0.25
    çĢı覽
    0.24
    éĥ¨åĪĨåĨħ容
    0.24
    acher
    0.23
     guest
    0.23
    temporary
    0.23
     Certain
    0.22
    tasks
    0.22
    restricted
    0.22
    Activations Density 0.021%

    No Known Activations