© 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. 48218
    Prev
    Next
    INDEX
    Explanations

    Jennifer followed by a name

    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
    ../../../
    -0.15
    iers
    -0.12
    ../../
    -0.11
    -fashioned
    -0.11
    ../../../../
    -0.10
    sWith
    -0.09
    ÑĩиÑģÑĤ
    -0.09
    iful
    -0.09
    edException
    -0.09
    vier
    -0.09
    POSITIVE LOGITS
    ãĥªãĥ³ãĤ°
    0.10
    jal
    0.10
    çĿ¬
    0.10
    ally
    0.09
    åīįèĢħ
    0.09
    anded
    0.09
    ếp
    0.09
    ault
    0.09
    ould
    0.09
    à¤
    0.09
    Activations Density 0.036%

    No Known Activations