© 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. 21979
    Prev
    Next
    INDEX
    Explanations

    instant messaging privacy settings

    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
    enerated
    -0.06
    ussa
    -0.06
    illo
    -0.06
     manifestation
    -0.06
    -multi
    -0.05
    .ibm
    -0.05
    ование
    -0.05
    iaga
    -0.05
    );\
    -0.05
     Stufe
    -0.05
    POSITIVE LOGITS
    ala
    0.05
    é£İæĻ¯
    0.05
     done
    0.05
    ipe
    0.05
     chiêm
    0.05
    led
    0.05
    éĹ®é¢ĺæĿ¥äºĨ
    0.05
    aling
    0.05
    alist
    0.05
    页第
    0.05
    Activations Density 0.095%

    No Known Activations