© 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. 1719
    Prev
    Next
    INDEX
    Explanations

    location or location context

    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
    è§ĦèĮĥåĮĸ
    -0.24
    åłĤ
    -0.23
    们çļĦ
    -0.22
    çīĽå¥¶
    -0.21
    .bio
    -0.21
    mime
    -0.21
     routines
    -0.21
    OfSize
    -0.21
     routine
    -0.20
     Routine
    -0.20
    POSITIVE LOGITS
     location
    0.37
     LOCATION
    0.35
    åľ°çĤ¹
    0.35
    (location
    0.34
    /location
    0.34
    ä½įç½®
    0.31
    åľ°çIJĨä½įç½®
    0.31
    ç»Ŀä½³
    0.31
     Location
    0.30
    é£İæĻ¯
    0.30
    Activations Density 0.018%

    No Known Activations