© 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. 30844
    Prev
    Next
    INDEX
    Explanations

    states and locations

    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
    åħ±å»º
    -0.10
     cams
    -0.09
    arend
    -0.09
    -Smith
    -0.08
    å®īéĺ²
    -0.08
    .fin
    -0.08
    anghai
    -0.08
    笳
    -0.08
    æ´ŀ
    -0.08
    çĶ·çĶŁ
    -0.08
    POSITIVE LOGITS
    çľ·
    0.11
    åIJĦçľģ
    0.10
    (states
    0.09
    çij°
    0.09
    éĻħ
    0.09
    CSR
    0.09
    åIJĦèĩªçļĦ
    0.09
    states
    0.09
    éļĽ
    0.09
    å¼Ģä¼ļ
    0.08
    Activations Density 0.086%

    No Known Activations