© 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. 58155
    Prev
    Next
    INDEX
    Explanations

    sign up for or subscribe to

    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
     Oasis
    -0.09
    Ñģп
    -0.09
    黩
    -0.09
    astle
    -0.08
    åħ±åIJĮä½ĵ
    -0.08
    çľļ
    -0.08
    Joined
    -0.08
     геÑĢо
    -0.08
    _initialize
    -0.08
     Pros
    -0.08
    POSITIVE LOGITS
    aid
    0.10
    å·¥ä½ľç»Ħ
    0.10
    dar
    0.09
    Assembly
    0.09
    å¤Ħåľ¨
    0.08
    ÑĤен
    0.08
    éĩijèŀįç§ijæĬĢ
    0.08
    ä¸Ńè¶ħ
    0.08
    oref
    0.08
    åįĬå²Ľ
    0.08
    Activations Density 0.016%

    No Known Activations