© 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. 23123
    Prev
    Next
    INDEX
    Explanations

    territory 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
    ä¸Ģ个éĹ®é¢ĺ
    -0.12
    éĹ®è´£
    -0.09
    颡
    -0.09
    çħ
    -0.09
    imum
    -0.08
    ลาย
    -0.08
    tracks
    -0.08
    ima
    -0.08
    -hearted
    -0.08
    ä»Ģä¹Īæł·
    -0.08
    POSITIVE LOGITS
    åĨħçļĦ
    0.13
    zelf
    0.12
     Ñģобой
    0.11
    istic
    0.10
    edly
    0.10
    éļį
    0.10
    arian
    0.09
    ç¬Ļ
    0.09
    ties
    0.09
    rag
    0.09
    Activations Density 0.007%

    No Known Activations