© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19550
    Prev
    Next
    INDEX
    Explanations

    economic costs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    ï¸
    -0.09
    两级
    -0.09
    åĬ©æīĭ
    -0.09
     Buy
    -0.08
    åIJĮæĥħ
    -0.08
    åħ¨éĿ¢åıijå±ķ
    -0.08
    çĥŃçĪ±
    -0.08
    _CRYPTO
    -0.08
    gle
    -0.08
    çĽĪåĪ©
    -0.08
    POSITIVE LOGITS
    æĪIJæľ¬
    0.19
     costs
    0.16
    çļĦæĪIJæľ¬
    0.15
     Costs
    0.14
    _costs
    0.14
     cost
    0.13
    ãĤ³ãĤ¹ãĥĪ
    0.13
    _cost
    0.13
    cost
    0.12
    Cost
    0.12
    Activations Density 0.042%

    No Known Activations