© 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. 31397
    Prev
    Next
    INDEX
    Explanations

    isolation or alone

    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
    ARCH
    -0.09
    è¡£
    -0.09
    ç²¾èĩ´
    -0.09
    Overrides
    -0.09
    IMIZE
    -0.09
    åı¯éĿłçļĦ
    -0.08
    åIJĪæ³ķ
    -0.08
    à¹Ĥà¸Ļ
    -0.08
    åIJĵ
    -0.08
    è¿ħ
    -0.08
    POSITIVE LOGITS
    åѤç«ĭ
    0.16
     isolation
    0.15
     isolated
    0.13
    éļĶ离
    0.12
    åѤ
    0.11
     isolate
    0.11
    isol
    0.10
     isol
    0.10
    ä¸İåħ¶ä»ĸ
    0.09
    çľŁç©º
    0.09
    Activations Density 0.053%

    No Known Activations