© 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. 5327
    Prev
    Next
    INDEX
    Explanations

    orientation

    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
    out
    -0.10
    nano
    -0.09
    hood
    -0.09
    ÙĪت
    -0.09
    jack
    -0.09
    çĵł
    -0.08
    åīį线
    -0.08
    ouver
    -0.08
    çľ¼æ³ª
    -0.08
    履约
    -0.08
    POSITIVE LOGITS
    ally
    0.14
    ¡
    0.10
    chestra
    0.10
    ALLY
    0.10
    ated
    0.10
     веÑī
    0.09
    缸åıį
    0.09
    gtest
    0.09
    ignal
    0.09
    amen
    0.09
    Activations Density 0.016%

    No Known Activations