© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53076
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

    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
    çIJ¨
    -0.09
    为åħ¶
    -0.09
    çĶļèĩ³
    -0.09
    åħ¶å®ĥéĹ®é¢ĺ
    -0.08
    åĪĩåħ¥
    -0.08
    fur
    -0.08
    çĶļèĩ³æĺ¯
    -0.08
    ieten
    -0.08
    deb
    -0.08
    æ·Ļ
    -0.08
    POSITIVE LOGITS
    ustum
    0.09
    -old
    0.09
    èµį
    0.09
    äºĨä¸Ģæī¹
    0.09
    çļ´
    0.08
    azer
    0.08
    _lit
    0.08
    adena
    0.08
    .idea
    0.08
    渤
    0.08
    Activations Density 0.158%

    No Known Activations