© 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. 12012
    Prev
    Next
    INDEX
    Explanations

    anonymous surfing, proxies

    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
    åĹĮ
    -0.10
    è´±
    -0.10
    ลà¸ĩ
    -0.09
    çĽį
    -0.09
    èݹ
    -0.09
    PEC
    -0.09
    èĤ¡
    -0.09
    çŁ³åĮĸ
    -0.09
    æĭ¾
    -0.08
    èį¯å¸Ī
    -0.08
    POSITIVE LOGITS
    å¤įåħ´
    0.10
     Cure
    0.10
    åĩºçĤī
    0.09
    å±Ĥå±Ĥ
    0.08
    lar
    0.08
     Circus
    0.08
    paper
    0.08
    æµĨ
    0.08
    çĸŁ
    0.08
    ekt
    0.08
    Activations Density 0.100%

    No Known Activations