© 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. 1563
    Prev
    Next
    INDEX
    Explanations

    import statement

    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
    ä»İä¸Ń
    -0.24
    æľīçĽĬ
    -0.24
    追
    -0.23
     advise
    -0.23
    èĸ°
    -0.23
     compliments
    -0.23
     tinder
    -0.22
     Curt
    -0.21
    ukes
    -0.21
    å¼Ģå±Ģ
    -0.21
    POSITIVE LOGITS
     Woj
    0.24
     Mag
    0.24
     Graham
    0.24
     verification
    0.22
    è¾Ī
    0.22
     DM
    0.21
     Maybe
    0.21
    åĥ¦
    0.21
     naked
    0.21
    (operator
    0.20
    Activations Density 0.019%

    No Known Activations