© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20099
    Prev
    Next
    INDEX
    Explanations

    HTML title tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    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
    à¸Ħà¹Į
    -0.05
    asen
    -0.05
    åĤ¬
    -0.05
    appa
    -0.05
    èĦ
    -0.05
    alay
    -0.05
    ìĭ
    -0.05
    åı¯ä»¥çIJĨ解
    -0.05
    FromClass
    -0.05
    éľ²å¤´
    -0.05
    POSITIVE LOGITS
    bankan
    0.06
    ities
    0.06
     mera
    0.06
    ihat
    0.06
    ermen
    0.06
    çĶŁæ´»ä¼ļ
    0.05
    çļĦå¼Ģ
    0.05
    itational
    0.05
    ulative
    0.05
    еÑĩ
    0.05
    Activations Density 0.002%

    No Known Activations