© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19062
    Prev
    Next
    INDEX
    Explanations

    grammatical structures and context related to prepositions

    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
    ugh
    -0.06
     quo
    -0.06
    åIJĪ
    -0.05
    æ³Ħ
    -0.05
    ér
    -0.05
    UF
    -0.05
    è¯
    -0.05
    omorphic
    -0.05
    /h
    -0.05
    åī§
    -0.05
    POSITIVE LOGITS
    说åĩºäºĨ
    0.06
    æ³ķ輪
    0.06
    è¡ĢçļĦ
    0.06
    à¹Ģà¸Ĺศ
    0.06
    åħ¶äºº
    0.06
    onestly
    0.06
    natur
    0.06
    inscrire
    0.06
    eszcze
    0.06
    market
    0.06
    Activations Density 0.020%

    No Known Activations