© 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. 17574
    Prev
    Next
    INDEX
    Explanations

    for purposes

    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
    äºĨ对
    -0.07
    گاÙĨ
    -0.06
    绩æķĪå¥ĸéĩij
    -0.06
    ÏĤ
    -0.06
    egral
    -0.06
    exe
    -0.05
    æ»ļæ»ļ
    -0.05
    agram
    -0.05
    ÑĢав
    -0.05
    åħ¬åħ±é¢Ħç®Ĺ
    -0.05
    POSITIVE LOGITS
    ggi
    0.06
    Ñĥго
    0.06
    tü
    0.06
    ãģ¾ãģĦ
    0.06
    ails
    0.06
    orny
    0.06
    itating
    0.06
    ؤÙĦاء
    0.06
    itates
    0.06
    PRI
    0.05
    Activations Density 0.011%

    No Known Activations