© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17517
    Prev
    Next
    INDEX
    Explanations

    this followed by identifier or descriptor

    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
    å®ŀçļĦ
    -0.06
    ombs
    -0.06
    cosa
    -0.06
    ä¸Ģç§įæĺ¯
    -0.05
     haja
    -0.05
    ØŃÙĬ
    -0.05
    anea
    -0.05
    å¤ļ大
    -0.05
    á»ģm
    -0.05
     real
    -0.05
    POSITIVE LOGITS
    _HINT
    0.06
    竺
    0.06
    ä¹ħ
    0.06
    æ³ĵ
    0.06
    çķĶ
    0.05
    äº
    0.05
    太åı¤
    0.05
    åĵī
    0.05
    è¨Ģ
    0.05
    postav
    0.05
    Activations Density 0.001%

    No Known Activations