© 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. 5925
    Prev
    Next
    INDEX
    Explanations

    registration forms and fees

    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
    æľ«
    -0.10
    åıĪ被
    -0.10
    ONY
    -0.09
    edes
    -0.09
    ened
    -0.09
    ä¸ĢçĤ¹
    -0.08
    æįĭ
    -0.08
    .Abs
    -0.08
    被è¯Ħ为
    -0.08
    ished
    -0.08
    POSITIVE LOGITS
    æ¸ł
    0.09
    -download
    0.09
    ngine
    0.09
    èĩªçĦ¶èĢĮçĦ¶
    0.09
    åĶ
    0.09
     tÆ°á»Ľng
    0.09
    解éĩĭ
    0.09
    zech
    0.08
    è¯łéĩĬ
    0.08
    asmus
    0.08
    Activations Density 0.011%

    No Known Activations