© 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. 49710
    Prev
    Next
    INDEX
    Explanations

    discrimination

    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
    òng
    -0.11
    strom
    -0.11
    itude
    -0.10
    åŃIJéĩĮ
    -0.10
    ays
    -0.09
    OfFile
    -0.09
    åħ¬å®īå±Ģ
    -0.09
    ä¸ŃåĽ½æ¢¦
    -0.09
     Stern
    -0.09
    èĩ¾
    -0.09
    POSITIVE LOGITS
    gle
    0.10
    iel
    0.09
    eter
    0.09
    ал
    0.08
    aise
    0.08
    eters
    0.08
    ogle
    0.08
    çĹ¢
    0.08
    项
    0.08
    å¾ħéģĩ
    0.08
    Activations Density 0.011%

    No Known Activations