© 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. 2626
    Prev
    Next
    INDEX
    Explanations

    subsidies and aid

    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
    soever
    -0.23
    ities
    -0.21
    cala
    -0.21
    ç»İ
    -0.21
    çģµ
    -0.19
    prises
    -0.19
    Merit
    -0.19
    à¸Ļà¸Ńà¸Ļ
    -0.19
    éĥģ
    -0.19
    å¤ĩ注
    -0.18
    POSITIVE LOGITS
    /free
    0.22
    edImage
    0.22
    åĴĮåıijå±ķ
    0.22
    丰åİļ
    0.20
    æģĭæĥħ
    0.20
    -cost
    0.20
    -backed
    0.20
    -free
    0.19
     Funds
    0.19
     payments
    0.19
    Activations Density 0.004%

    No Known Activations