© 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. 27968
    Prev
    Next
    INDEX
    Explanations

    scale-up and preparation

    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
    çĥŃæ½®
    -0.10
    nero
    -0.09
    allee
    -0.09
    /xhtml
    -0.09
    çľĭäºĨä¸Ģ
    -0.09
    çģ«æĺŁ
    -0.09
    Creators
    -0.09
    深深çļĦ
    -0.09
    çģ«
    -0.08
    _ttl
    -0.08
    POSITIVE LOGITS
    åķĨä¸ļåĮĸ
    0.10
    éĩı产
    0.10
    scaling
    0.09
    ä¸ĭ鼨
    0.09
    大è§Ħ模
    0.09
     scaling
    0.09
    auf
    0.09
    è§Ħ模åĮĸ
    0.08
    æī©å±ķ
    0.08
    è§Ħ模
    0.08
    Activations Density 0.072%

    No Known Activations