© 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. 17149
    Prev
    Next
    INDEX
    Explanations

    primary keys and ids

    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
    olia
    -0.10
    APS
    -0.10
    ÑĦÑĢ
    -0.09
    å®ĿèĹı
    -0.09
    sher
    -0.09
    WithContext
    -0.09
    è°¥
    -0.09
    thur
    -0.09
    å¹²äºĭ
    -0.08
    åºĸ
    -0.08
    POSITIVE LOGITS
    æłĩè¯Ĩ
    0.13
    æłĩè®°
    0.12
    è¯ĨåĪ«
    0.11
    èŃĺ
    0.10
     ID
    0.10
    æłĩå¿Ĺ
    0.09
    è¯ģ件
    0.09
     collar
    0.09
    è¯Ĩ
    0.09
    身份è¯ģ
    0.09
    Activations Density 0.152%

    No Known Activations