© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 32265
    Prev
    Next
    INDEX
    Explanations

    Todays

    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
    eus
    -0.10
    rema
    -0.09
    eil
    -0.09
    çĶ«
    -0.09
    ANCH
    -0.09
    ieren
    -0.09
    еÑĢж
    -0.09
    STREAM
    -0.09
    é©°
    -0.09
    åĵĪå°Ķ
    -0.09
    POSITIVE LOGITS
    缮åīį为æŃ¢
    0.13
    ting
    0.11
    gether
    0.10
    为æŃ¢
    0.10
    éĵĭ
    0.09
    çĤ¬
    0.09
    lu
    0.09
    -old
    0.09
    æĦıä¹īä¸ĬçļĦ
    0.09
    æĹºçĽĽ
    0.08
    Activations Density 0.018%

    No Known Activations