© 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. 62481
    Prev
    Next
    INDEX
    Explanations

    essential and imperative conjunctions

    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
    ç¯ĩ
    -0.09
     cola
    -0.08
    jit
    -0.08
     hoe
    -0.08
     воÑĤ
    -0.08
    æºIJäºİ
    -0.08
    为æĬĵ
    -0.08
    ANTI
    -0.08
    ervo
    -0.08
     Morton
    -0.08
    POSITIVE LOGITS
    æ±
    0.11
    æ°¢èĥ½
    0.10
    å®Īä½ı
    0.10
    ê¶Į
    0.10
    æĪij们å¿ħé¡»
    0.10
    åħ³éŨ
    0.09
    ëĿ¼ëıĦ
    0.09
    亲è¿ij
    0.09
    æľīå¿ħè¦ģ
    0.09
    ëĮĢë¡ľ
    0.09
    Activations Density 0.047%

    No Known Activations