© 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. 1140
    Prev
    Next
    INDEX
    Explanations

    list separators

    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
    vä
    -0.23
    ward
    -0.23
    è£ħè½½
    -0.22
    imer
    -0.21
    /stat
    -0.21
    åĽ½èµĦå§Ķ
    -0.21
    æ°¸æģĴ
    -0.21
    åľ¨åĨħçļĦ
    -0.21
     generously
    -0.20
    罡
    -0.20
    POSITIVE LOGITS
     ModelState
    0.25
     Uph
    0.24
    индивид
    0.24
    еÑģÑĤеÑģÑĤвенн
    0.23
     Minor
    0.23
     Param
    0.22
     Slash
    0.22
     converters
    0.22
     chatt
    0.22
     worse
    0.22
    Activations Density 0.036%

    No Known Activations