© 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. 39793
    Prev
    Next
    INDEX
    Explanations

    purification and chromatography techniques

    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
    éļ°
    -0.09
    PIN
    -0.09
    è§ģè¯ģ
    -0.09
    驶
    -0.09
    auer
    -0.09
    duk
    -0.09
    æĶ¯çº¿
    -0.09
    è§Ĥçľĭ
    -0.09
    çĸ²
    -0.09
    å¨Ĩ
    -0.09
    POSITIVE LOGITS
    èĽĭ
    0.10
     prote
    0.09
    éĩįéĩį
    0.08
    ,function
    0.08
    æŬ
    0.08
     centrif
    0.08
    åħľ
    0.08
    Specifies
    0.08
    åįģæĿ¡
    0.08
    urt
    0.08
    Activations Density 0.469%

    No Known Activations