© 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. 17780
    Prev
    Next
    INDEX
    Explanations

    positive sentiment evaluators

    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
     chosen
    -0.06
    thood
    -0.05
    eno
    -0.05
     those
    -0.05
     chose
    -0.05
    those
    -0.05
     choosing
    -0.05
    atra
    -0.05
    enen
    -0.05
     du
    -0.05
    POSITIVE LOGITS
    åıijçĶŁåľ¨
    0.07
    åıijçĶŁäºİ
    0.06
    inge
    0.06
    æľĢæľīæķĪ
    0.06
    à¸Ļม
    0.06
     womens
    0.06
    eldorf
    0.06
     ÙĬÙĩÙħ
    0.06
    ingar
    0.06
    alborg
    0.06
    Activations Density 0.142%

    No Known Activations