© 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. 17028
    Prev
    Next
    INDEX
    Explanations

    request suggestion

    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
    ossier
    -0.06
    æĽ´åħ·
    -0.06
    iard
    -0.06
    chrift
    -0.05
    stig
    -0.05
    å®ŀçĶ¨
    -0.05
    äºĨä¸Ģ份
    -0.05
     sanitaire
    -0.05
     briefed
    -0.05
    roach
    -0.05
    POSITIVE LOGITS
    ities
    0.09
    ails
    0.07
    ences
    0.06
    ugs
    0.06
    aille
    0.06
    eras
    0.06
    ors
    0.06
    ä¸įæģ¯
    0.06
    ä¹İ
    0.06
    ident
    0.06
    Activations Density 0.017%

    No Known Activations