© 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. 2348
    Prev
    Next
    INDEX
    Explanations

    raf, pector, alam

    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
    çĩİ
    -0.10
    åĤĢ
    -0.10
    ackers
    -0.10
    åľ©
    -0.09
     Gul
    -0.09
    éĨļ
    -0.09
    ä¸įåĥı
    -0.09
    èĩªçĦ¶çģ¾å®³
    -0.09
    oir
    -0.09
    raig
    -0.09
    POSITIVE LOGITS
    çī§åľº
    0.10
    æ§İ
    0.09
    穹
    0.09
    çīĿ
    0.09
    less
    0.08
    åİĨåı²æĸ°
    0.08
    sms
    0.08
    âĺħâĺħ
    0.08
    缸è§ģ
    0.08
    åĨľåľº
    0.08
    Activations Density 0.003%

    No Known Activations