© 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. 20083
    Prev
    Next
    INDEX
    Explanations

    questions asking for options

    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
    ia
    -0.06
    Å¡ti
    -0.06
    ette
    -0.06
    der
    -0.06
    anti
    -0.06
     unit
    -0.06
    uv
    -0.05
    ons
    -0.05
    unit
    -0.05
    åĢ¦
    -0.05
    POSITIVE LOGITS
    feu
    0.06
    /Instruction
    0.06
    кÑĥда
    0.06
    ìĺ¤ê³ł
    0.06
    à¸ļ
    0.06
     wereld
    0.05
    atsu
    0.05
    æĢİä¹Īèµ°
    0.05
    кÑĢо
    0.05
    é¦ģ
    0.05
    Activations Density 0.005%

    No Known Activations