© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16806
    Prev
    Next
    INDEX
    Explanations

    fetching and loading data

    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
    dot
    -0.05
    h
    -0.05
    夹
    -0.05
    ee
    -0.05
     cot
    -0.05
    arks
    -0.05
    毫
    -0.05
     cons
    -0.05
     clamp
    -0.05
     dot
    -0.05
    POSITIVE LOGITS
    æħµ
    0.07
    zett
    0.07
     xtype
    0.07
    Ủ
    0.06
    ereal
    0.06
    ETTO
    0.06
    istine
    0.06
    æĹıçļĦ
    0.06
    _ping
    0.06
    elado
    0.06
    Activations Density 0.129%

    No Known Activations