© 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. 1831
    Prev
    Next
    INDEX
    Explanations

    self-perception, promotion, consciousness, transformation

    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
    à¹ģร
    -0.10
    unde
    -0.09
    bounce
    -0.09
    uite
    -0.09
    odom
    -0.09
    åĪĨæł¡
    -0.09
    çĹī
    -0.09
    umpy
    -0.08
    .pa
    -0.08
    bö
    -0.08
    POSITIVE LOGITS
    /self
    0.13
    (Self
    0.13
    self
    0.09
    裤
    0.09
    å¾ĹæĦı
    0.09
    éħ¿
    0.09
    ständ
    0.09
    ØŃÙĦ
    0.09
    der
    0.09
     Ban
    0.09
    Activations Density 0.065%

    No Known Activations