© 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. 36192
    Prev
    Next
    INDEX
    Explanations

    unlocking, hacking, or bypassing systems

    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
    ROL
    -0.08
    è¦ģæĬĬ
    -0.08
    è¦ģç´§
    -0.08
    éĽĨç»ĵ
    -0.08
    èĨ³
    -0.08
    -central
    -0.07
    俳
    -0.07
    mus
    -0.07
     convenient
    -0.07
    awai
    -0.07
    POSITIVE LOGITS
    伪
    0.11
    æĪĴ
    0.10
    ç²ī
    0.10
     legalization
    0.10
    åIJĪæ³ķ
    0.10
    arrants
    0.10
    ç±³ç²ī
    0.10
    åIJĪæ³ķæĢ§
    0.09
    .fake
    0.09
    åĪ·
    0.09
    Activations Density 0.309%

    No Known Activations