© 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. 19902
    Prev
    Next
    INDEX
    Explanations

    ai related names and text fragments

    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
    ally
    -0.15
    ality
    -0.10
    ãģĹãģ¾ãģĦ
    -0.10
    ãģĹãģ¾
    -0.10
    edImage
    -0.10
    sr
    -0.09
    èĶ¼
    -0.09
    sen
    -0.09
    cher
    -0.09
    sel
    -0.09
    POSITIVE LOGITS
    0.12
    ropa
    0.11
    plemented
    0.10
    çĿĩ
    0.09
    plied
    0.09
    oment
    0.09
    ient
    0.09
    kea
    0.09
    lement
    0.08
    irth
    0.08
    Activations Density 0.067%

    No Known Activations