© 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. 35146
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    å¹ķ
    -0.09
    าะ
    -0.08
    æĦł
    -0.08
     chance
    -0.08
    YLE
    -0.08
    å¸ħ
    -0.08
    é¹Ĺ
    -0.08
    soever
    -0.08
    èĦĸ
    -0.08
    .setCharacter
    -0.08
    POSITIVE LOGITS
    izable
    0.11
    æ³īæ°´
    0.10
    ening
    0.10
    dux
    0.09
    reen
    0.09
    å®Ŀå®ī
    0.09
     Paz
    0.09
    æĥĩ
    0.08
    .pm
    0.08
    -real
    0.08
    Activations Density 0.000%

    No Known Activations