© 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. 11605
    Prev
    Next
    INDEX
    Explanations

    licorice

    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
    çĻĥ
    -0.10
    çıī
    -0.09
    oose
    -0.09
    contexts
    -0.09
    æĤ¬å¿µ
    -0.09
    çľĭå¾ħ
    -0.09
    IBC
    -0.09
     ÑģпÑĢав
    -0.09
    åŃ
    -0.09
    æºı
    -0.09
    POSITIVE LOGITS
    ÑĢÑıд
    0.09
     Swords
    0.09
    ument
    0.08
     Roths
    0.08
    ä¸ĩ象
    0.08
    æłijæŀĿ
    0.07
    odia
    0.07
    å¤ĸå¥Ĺ
    0.07
    /mock
    0.07
     Abbey
    0.07
    Activations Density 0.004%

    No Known Activations