© 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. 35517
    Prev
    Next
    INDEX
    Explanations

    Israeli politics and conflict

    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
     télécharg
    -0.10
    raud
    -0.09
    opoly
    -0.09
    utches
    -0.09
    ouro
    -0.09
    croll
    -0.08
    åIJİèĢħ
    -0.08
    åľ¨ä¸Ģ
    -0.08
    olutions
    -0.08
    -loading
    -0.08
    POSITIVE LOGITS
    æĸ°ä¸Ģ代
    0.09
    ymm
    0.08
    管æݧ
    0.08
    ç¡ĸ
    0.08
    @author
    0.08
    åĴ«
    0.08
     ceasefire
    0.08
     ÑģÑĤан
    0.08
    èijĹ
    0.08
    交ç»ĩ
    0.08
    Activations Density 0.090%

    No Known Activations