© 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. 796
    Prev
    Next
    INDEX
    Explanations

    warehousing or ware

    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
    sWith
    -0.27
    ENDING
    -0.20
    ually
    -0.20
    ALLY
    -0.19
    swith
    -0.19
    æ¹ĥ
    -0.19
    EObject
    -0.19
    uate
    -0.18
     bargain
    -0.18
    岸
    -0.18
    POSITIVE LOGITS
    housing
    0.27
    chaft
    0.23
    zia
    0.22
    fare
    0.22
    centage
    0.21
    cent
    0.21
    shed
    0.20
    yard
    0.20
    omens
    0.20
    iginal
    0.19
    Activations Density 0.025%

    No Known Activations