© 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. 883
    Prev
    Next
    INDEX
    Explanations

    dropping a hint

    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
    ä¹ĭç¾İ
    -0.26
    engl
    -0.25
    ä¹ĭå¤ľ
    -0.25
    WithEmail
    -0.23
    åĨĮ
    -0.22
     Nurs
    -0.22
    ...]↵↵
    -0.21
    abox
    -0.21
     Levine
    -0.21
    aminer
    -0.20
    POSITIVE LOGITS
    ights
    0.29
    imson
    0.24
    S
    0.23
    Hint
    0.23
    Copy
    0.23
    broker
    0.23
    bra
    0.23
    éģĹå¿ĺ
    0.23
    Params
    0.23
    pii
    0.22
    Activations Density 0.004%

    No Known Activations