© 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. 5634
    Prev
    Next
    INDEX
    Explanations

    `file` marker

    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
    该éĻ¢
    -0.09
    è¿Ļæł·æīįèĥ½
    -0.08
    çŀij
    -0.08
    ÑģпоÑĢ
    -0.08
    3
    -0.08
    åĬ¿å¿ħ
    -0.08
    loi
    -0.07
    4
    -0.07
    å©¿
    -0.07
    6
    -0.07
    POSITIVE LOGITS
    intree
    0.10
    uating
    0.10
    说æĪij
    0.10
    âŀ£
    0.09
    é£İäºij
    0.09
    stin
    0.09
    路桥
    0.09
    érica
    0.09
    .tensor
    0.09
    _PARTITION
    0.08
    Activations Density 0.035%

    No Known Activations