© 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. 21024
    Prev
    Next
    INDEX
    Explanations

    bias and its modifications

    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
     Statt
    -0.06
    ive
    -0.06
    çī¹åĪ«æ³¨æĦı
    -0.06
     xÃŃ
    -0.06
    atts
    -0.05
     ëĤĺìĦ°ëĭ¤
    -0.05
    reis
    -0.05
    orse
    -0.05
    acus
    -0.05
    è°Ī
    -0.05
    POSITIVE LOGITS
    hern
    0.06
    åĸĦ
    0.06
    elly
    0.06
    enth
    0.06
    ety
    0.06
    reté
    0.05
    åŃĺåľ¨äºİ
    0.05
    etur
    0.05
    Ø®Ùħ
    0.05
    emente
    0.05
    Activations Density 0.003%

    No Known Activations