© 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. 39273
    Prev
    Next
    INDEX
    Explanations

    not able / not for / not selected

    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
    UPPORT
    -0.10
    бин
    -0.10
    éķ¿éķ¿
    -0.08
    èĮµ
    -0.08
    hes
    -0.08
    çŀĦ
    -0.08
    uhe
    -0.08
    ONY
    -0.08
     çalÄ±ÅŁmalar
    -0.08
    hel
    -0.08
    POSITIVE LOGITS
    zs
    0.09
    çĦ¶æĺ¯
    0.09
    ably
    0.09
    ional
    0.09
    ledge
    0.09
    ape
    0.09
    çĪ·
    0.09
    个åĪ«
    0.09
    个人è§ĤçĤ¹
    0.08
    ä¸Ģ件äºĭ
    0.08
    Activations Density 0.075%

    No Known Activations