© 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. 20909
    Prev
    Next
    INDEX
    Explanations

    secret or key identifier

    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
    ä¸įè¾¾
    -0.05
    -progress
    -0.05
     factual
    -0.05
    å¼łè´´
    -0.05
    isos
    -0.05
    çĸĹ
    -0.05
    è§Ħå®ļ
    -0.05
    dain
    -0.05
    yg
    -0.05
    еÑīа
    -0.05
    POSITIVE LOGITS
    CLR
    0.06
    kop
    0.06
    loff
    0.06
    utr
    0.06
    ãĥ¼ãĤ¸ãĥ¼
    0.06
    edi
    0.05
    ungan
    0.05
    æĹłåIJį
    0.05
     consort
    0.05
    omic
    0.05
    Activations Density 0.004%

    No Known Activations