© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19575
    Prev
    Next
    INDEX
    Explanations

    to address this issue

    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
    opard
    -0.06
    å¤Ł
    -0.06
     Blasio
    -0.05
     باش
    -0.05
    åĮħè£ħ
    -0.05
     partir
    -0.05
    ÙĤÙĬÙĤ
    -0.05
    åħ¬åħ±é¢Ħç®Ĺ
    -0.05
    ä¹İ
    -0.05
    çŁ¥è¶³
    -0.05
    POSITIVE LOGITS
    raising
    0.06
    asti
    0.05
    ä½
    0.05
    æĮģç»ŃæıIJåįĩ
    0.05
    o
    0.05
    ãģ¼
    0.05
    ummer
    0.05
     Spre
    0.05
    em
    0.05
    fter
    0.05
    Activations Density 0.023%

    No Known Activations