© 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. 27582
    Prev
    Next
    INDEX
    Explanations

    Ash followed by 'es', 'burn', 'land', 'field', 'ley'

    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
    çĤĴèĤ¡
    -0.09
    AINER
    -0.09
    .LinkedList
    -0.09
    _PROCESS
    -0.08
    Å¡t
    -0.08
    Ñĩи
    -0.08
    çŁ³æ²¹åĮĸå·¥
    -0.08
    asper
    -0.08
    ivity
    -0.08
    ëĤľ
    -0.08
    POSITIVE LOGITS
    fully
    0.11
    croft
    0.10
    phalt
    0.10
    åĪ©äºİ
    0.10
    fall
    0.10
    èĥ½æī¾åĪ°
    0.09
    coat
    0.09
    ะ
    0.09
    çĦ¶æĺ¯
    0.09
    0.09
    Activations Density 0.011%

    No Known Activations