© 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. 18060
    Prev
    Next
    INDEX
    Explanations

    the concept of about

    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
    ural
    -0.05
    multiline
    -0.05
    以
    -0.05
    以éĺ²
    -0.05
    å±ŀäºİ
    -0.05
    使çĶ¨è¯´æĺİ
    -0.05
    algo
    -0.05
    ice
    -0.05
    å®ļæľŁ
    -0.05
    hat
    -0.05
    POSITIVE LOGITS
    ÙĪÙĬات
    0.06
    schlieÃŁend
    0.06
    ellig
    0.06
     timings
    0.06
    rar
    0.06
    åij½è¿IJåħ±åIJĮä½ĵ
    0.06
    ÑģÑĤави
    0.06
    tabil
    0.06
    ç®Ķ
    0.06
    verständlich
    0.06
    Activations Density 0.014%

    No Known Activations