© 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. 61897
    Prev
    Next
    INDEX
    Explanations

    remarkable achievements or exploits

    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
    yard
    -0.09
    人寿
    -0.09
    gettext
    -0.09
    欣
    -0.09
    ya
    -0.09
    esi
    -0.09
    iani
    -0.08
    volution
    -0.08
    éħª
    -0.08
    hair
    -0.08
    POSITIVE LOGITS
    ively
    0.13
    istic
    0.11
    iveness
    0.11
    iful
    0.10
    åĦ¿
    0.09
    ä¹ĭå¤Ħ
    0.09
    ives
    0.09
    ISTIC
    0.09
    uell
    0.09
    ably
    0.09
    Activations Density 0.002%

    No Known Activations