© 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. 30548
    Prev
    Next
    INDEX
    Explanations

    Pax officials, RAX, StaxServer, Raxone

    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
    icher
    -0.10
    èĭĶ
    -0.09
    å¼Ģæ°´
    -0.09
    umo
    -0.09
    aling
    -0.08
    ouser
    -0.08
    éĻ©
    -0.08
     McGu
    -0.08
    ors
    -0.08
    aven
    -0.08
    POSITIVE LOGITS
    è¹²
    0.09
    æĹ¶æľŁçļĦ
    0.08
    åĪ©äºİ
    0.08
    æĴ¤ç¦»
    0.08
    ière
    0.08
    纬
    0.08
     голоÑģ
    0.08
    REQUIRED
    0.08
    IMUM
    0.08
    า
    0.08
    Activations Density 0.027%

    No Known Activations