© 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. 17257
    Prev
    Next
    INDEX
    Explanations

    gone or went followed by on/back/viral/well

    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
    ãĥ³
    -0.09
     söz
    -0.09
    gend
    -0.09
    éłĵ
    -0.09
    inned
    -0.09
    åĨįçİ°
    -0.08
    çIJ¥
    -0.08
    èŀĤ
    -0.08
    _ENCODING
    -0.08
     powerhouse
    -0.08
    POSITIVE LOGITS
    çķ´
    0.09
    BufferData
    0.09
    è´Ŀ壳
    0.09
    ration
    0.09
    rum
    0.09
    æ·±å±Ĥ次
    0.09
    人æĢ§åĮĸ
    0.08
    绿èī²çݯä¿Ŀ
    0.08
    æĬīæĭ©
    0.08
    è£ģåijĺ
    0.08
    Activations Density 0.036%

    No Known Activations