© 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. 5095
    Prev
    Next
    INDEX
    Explanations

    I say / I am / I'm

    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
    èĢĮåľ¨
    -0.10
    exo
    -0.09
    ibern
    -0.09
    udit
    -0.09
    LAN
    -0.09
    IFIER
    -0.09
     jakie
    -0.08
    身æĹģ
    -0.08
    æľŁ
    -0.08
    atrib
    -0.08
    POSITIVE LOGITS
     заÑĤем
    0.09
    éĥ½éĿŀ常
    0.08
    éĩįå·¥
    0.08
    è¦ĸçĤº
    0.08
    è§Ĩ为
    0.08
    flu
    0.08
    大åĬĽ
    0.08
    åģļåĪ°
    0.08
    ear
    0.08
    èµĦ
    0.08
    Activations Density 0.044%

    No Known Activations