© 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. 32758
    Prev
    Next
    INDEX
    Explanations

    point of

    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
    athy
    -0.10
    itte
    -0.09
    inding
    -0.09
    _timing
    -0.09
     dof
    -0.09
    çľ¼éĩĮ
    -0.09
    庹
    -0.09
    åıijå±ķ空éĹ´
    -0.09
    è¦ģç´§
    -0.09
    ä¸ĢåľĪ
    -0.09
    POSITIVE LOGITS
    iful
    0.10
    erable
    0.09
    less
    0.09
    çľĩ
    0.08
     зÑĢениÑı
    0.08
     cá»Ń
    0.08
     point
    0.08
    POINT
    0.08
    éĺķ
    0.08
    .point
    0.08
    Activations Density 0.021%

    No Known Activations