© 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. 57263
    Prev
    Next
    INDEX
    Explanations

    agreement / agreed to / between

    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
    idal
    -0.09
    åĮĸçļĦ
    -0.09
    ifer
    -0.09
     же
    -0.09
    ếp
    -0.09
    ç½ħ
    -0.09
    quoi
    -0.09
    ugal
    -0.09
    inate
    -0.09
    ering
    -0.09
    POSITIVE LOGITS
    orio
    0.12
    ably
    0.10
    EMENT
    0.10
    паÑĢ
    0.10
    ement
    0.10
    ance
    0.10
    ATS
    0.10
     اÙĦÙħص
    0.10
    antic
    0.09
    ships
    0.09
    Activations Density 0.043%

    No Known Activations