© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23837
    Prev
    Next
    INDEX
    Explanations

    within six games

    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
    noinspection
    -0.11
    รม
    -0.10
    åĢĴå¡Į
    -0.09
    åħ¨æĹ¥åĪ¶
    -0.08
    collapse
    -0.08
    çĽijæĬ¤
    -0.08
    çļĦä¿¡ä»»
    -0.08
    æijĩ
    -0.08
    å´©æºĥ
    -0.08
    åºĨ幸
    -0.08
    POSITIVE LOGITS
    (Equal
    0.10
    åĽ°æī°
    0.09
    åIJĥè¿ĩ
    0.09
    亲çĪ±
    0.09
    å
    0.08
    åĴĦ
    0.08
     пÑĢовед
    0.08
    oup
    0.08
    åİķ
    0.08
     ARG
    0.08
    Activations Density 0.002%

    No Known Activations