© 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. 1135
    Prev
    Next
    INDEX
    Explanations

    sale or sold

    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
    CSI
    -0.10
     dap
    -0.09
    ODO
    -0.09
    isper
    -0.09
    æŀľåĽŃ
    -0.09
    vsp
    -0.08
    _timezone
    -0.08
    ãĤ¤ãĥ¤
    -0.08
    IndexOf
    -0.08
    çĦ¶
    -0.08
    POSITIVE LOGITS
    iah
    0.08
    æıª
    0.08
    mits
    0.08
    çģ«è½¦
    0.08
    以人æ°ij
    0.08
    çIJĩ
    0.08
    lav
    0.08
    ello
    0.08
    åĸľæ¬¢åIJĥ
    0.08
     Ramirez
    0.08
    Activations Density 0.005%

    No Known Activations