© 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. 36215
    Prev
    Next
    INDEX
    Explanations

    vacation rentals

    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
    lessly
    -0.10
    å§Ĭ
    -0.10
    ãģ£ãģ¨
    -0.10
     rÃłng
    -0.10
    igner
    -0.09
    arning
    -0.09
    CAPE
    -0.09
    ument
    -0.09
    hole
    -0.09
    -up
    -0.09
    POSITIVE LOGITS
    ary
    0.11
    ally
    0.10
    eer
    0.10
    adel
    0.10
    autocomplete
    0.09
    åĪ¶åº¦æĶ¹éĿ©
    0.09
    sWith
    0.08
    ouched
    0.08
    rieb
    0.08
    çĶ¨åľ°
    0.08
    Activations Density 0.013%

    No Known Activations