© 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. 20852
    Prev
    Next
    INDEX
    Explanations

    involved in

    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
    erti
    -0.06
    iae
    -0.06
    rif
    -0.06
    apta
    -0.06
    Clientes
    -0.06
    optimizer
    -0.06
    åĪĨäºĨ
    -0.06
    æīĭæı¡
    -0.05
    Entries
    -0.05
    åIJİèĩ³
    -0.05
    POSITIVE LOGITS
     involves
    0.08
     involve
    0.08
     involving
    0.08
     involvement
    0.06
     involved
    0.06
    ing
    0.06
    åıijçĶŁåľ¨
    0.06
    æ¶īåıĬ
    0.06
    æ¶īåıĬåĪ°
    0.05
    actic
    0.05
    Activations Density 0.016%

    No Known Activations