© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3450
    Prev
    Next
    INDEX
    Explanations

    targeting

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    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
    ìĨŁ
    -0.21
     voluntarily
    -0.20
    .BASELINE
    -0.20
     Bender
    -0.20
    åħģ
    -0.19
    .AWS
    -0.19
    .Xaml
    -0.19
    apsed
    -0.19
    .splice
    -0.19
    ovenant
    -0.19
    POSITIVE LOGITS
     targeting
    0.30
    严åİī
    0.26
     targeted
    0.26
    -target
    0.25
    æĥ©ç½ļ
    0.24
    åĪ¶è£ģ
    0.24
    对ä»ĺ
    0.24
    åīĭ
    0.22
    åĬłå¤§å¯¹
    0.22
    ä¾Ŀæ³ķ追究
    0.22
    Activations Density 0.820%

    No Known Activations