© 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. 5006
    Prev
    Next
    INDEX
    Explanations

    protein interactions and binding sites

    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
    褥
    -0.10
    æĴ¬
    -0.10
    ebin
    -0.09
    è¾ķ
    -0.09
     recuper
    -0.08
    çĮĹ
    -0.08
    fluid
    -0.08
    ä½ĵèĤ²
    -0.08
    æĬĺå°Ħ
    -0.08
    è¯Ŀé¢ĺ
    -0.08
    POSITIVE LOGITS
    /interface
    0.09
    simd
    0.09
    æŀĦçŃij
    0.09
    ×ķ×Ŀ
    0.08
     Mueller
    0.08
    æľĪèĸª
    0.08
    èĩªè´Ł
    0.08
    ÑĢоÑģÑĤ
    0.08
    .RESULT
    0.08
    .parts
    0.08
    Activations Density 0.514%

    No Known Activations