© 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. 17069
    Prev
    Next
    INDEX
    Explanations

    official compilation or reports

    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
    åħ®
    -0.06
    ä»ħ代表
    -0.06
    eurs
    -0.06
    Spatial
    -0.06
    abor
    -0.06
    个人çļĦ
    -0.06
    åľ°çIJĨä½įç½®
    -0.05
    ezd
    -0.05
    atial
    -0.05
    éĩĩ访æĹ¶è¡¨ç¤º
    -0.05
    POSITIVE LOGITS
    åħ¬ç¤º
    0.06
    sted
    0.06
    çļĦæľ¬
    0.05
     ÑģвеÑĢ
    0.05
     both
    0.05
     equivalence
    0.05
     sacrifice
    0.05
    æķ°ä»¥
    0.05
    æĺ¯åħĪ
    0.05
    elfare
    0.05
    Activations Density 0.052%

    No Known Activations