© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9724
    Prev
    Next
    INDEX
    Explanations

    injection or syringes

    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
    .ft
    -0.11
    .sb
    -0.09
    sandbox
    -0.09
    说åĩº
    -0.08
     organ
    -0.08
    ortion
    -0.08
    çıī
    -0.08
    ÑĢиÑģ
    -0.08
     Pant
    -0.08
    uario
    -0.08
    POSITIVE LOGITS
    注å°Ħ
    0.20
     Injection
    0.16
     injection
    0.16
     inject
    0.16
     injections
    0.15
    .inject
    0.15
    Inject
    0.15
    inject
    0.14
    Injection
    0.14
    注åħ¥
    0.13
    Activations Density 0.273%

    No Known Activations