© 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. 20512
    Prev
    Next
    INDEX
    Explanations

    deposit accounts

    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
    åŃĺéĩı
    -0.06
    麻çĥ¦
    -0.06
     downstream
    -0.06
    èµĶ
    -0.06
    bury
    -0.06
    ownload
    -0.06
    erne
    -0.06
    ä¸ĭåİ»
    -0.06
    ä½İåİĭ
    -0.06
     downloadable
    -0.06
    POSITIVE LOGITS
     cooper
    0.06
    èĬ±å²Ĺ岩
    0.06
     thermal
    0.06
    è¶ħè¿ĩ约
    0.05
    计
    0.05
    submitted
    0.05
    رار
    0.05
    scient
    0.05
    å¦ĤèĬ±
    0.05
    اتÛĮ
    0.05
    Activations Density 0.010%

    No Known Activations