© 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. 2833
    Prev
    Next
    INDEX
    Explanations

    contribute, volunteers, help, needed

    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
    antics
    -0.24
    illon
    -0.23
     unified
    -0.23
     survival
    -0.22
    äºĨä»ĸçļĦ
    -0.21
    cribed
    -0.21
    第ä¸īèĢħ
    -0.21
     followed
    -0.21
    InstanceState
    -0.21
     improperly
    -0.21
    POSITIVE LOGITS
    åıĤä¸İåĪ°
    0.27
    æĪĸå¤ļ
    0.27
    æľīåħ´è¶£
    0.26
    venir
    0.25
    è¶Ĭå¤ļ
    0.25
    æĪĸ
    0.24
    è¯ķè¡Į
    0.24
    usto
    0.23
    åı¯ä¾Ľ
    0.23
     algun
    0.23
    Activations Density 0.032%

    No Known Activations