© 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. 3004
    Prev
    Next
    INDEX
    Explanations

    mountain with subsequent words

    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
    ubic
    -0.22
    NewLabel
    -0.20
    主任
    -0.19
     Bris
    -0.19
    æ¯įæł¡
    -0.18
    ë¥ł
    -0.18
    ilig
    -0.18
    æ°ijæĦı
    -0.18
    mys
    -0.17
    ä¸įçĦ¶
    -0.17
    POSITIVE LOGITS
    ized
    0.27
    ous
    0.27
    rise
    0.23
    æ¥Ĥ
    0.23
    ization
    0.22
     russe
    0.22
    ville
    0.20
    å£ij
    0.20
    IZER
    0.20
    åľ°å¸¦
    0.20
    Activations Density 0.012%

    No Known Activations