© 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. 18890
    Prev
    Next
    INDEX
    Explanations

    finding requirements

    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¤ļç±³
    -0.06
    unt
    -0.06
    Ùĩد
    -0.06
    ria
    -0.06
    potensi
    -0.06
    çľĭåĪ°è¿Ļ
    -0.06
    æ¸ħæ³ī
    -0.06
    oin
    -0.05
    ary
    -0.05
    rans
    -0.05
    POSITIVE LOGITS
     dint
    0.06
    Opts
    0.05
    æ´²
    0.05
    æijĬ
    0.05
    æłĩ
    0.05
    OrDefault
    0.05
    /her
    0.05
    åºĦ
    0.05
    hani
    0.05
     vegetarian
    0.05
    Activations Density 0.004%

    No Known Activations