© 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. 1157
    Prev
    Next
    INDEX
    Explanations

    peer review, jury, judges

    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
    lements
    -0.24
     chatt
    -0.24
     Rentals
    -0.24
     Representation
    -0.23
    åıijå±ķä¸Ń
    -0.23
    amed
    -0.23
    entric
    -0.23
     traded
    -0.23
     ICommand
    -0.22
     renegot
    -0.22
    POSITIVE LOGITS
    è¯Ħå§Ķ
    0.49
    è¯Ħ审
    0.49
    è¯ĦåĪĨ
    0.40
    ç»Ħéķ¿
    0.36
    è¯Ħ
    0.36
    è¯Ħè®®
    0.36
    å®¡æł¸
    0.35
     reviewers
    0.35
     judges
    0.35
    éģ´éĢī
    0.35
    Activations Density 0.049%

    No Known Activations