© 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. 19806
    Prev
    Next
    INDEX
    Explanations

    initial and optional

    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
    å¾ħ
    -0.06
    ä¸įä½ľ
    -0.06
     Tro
    -0.05
    dda
    -0.05
     Rot
    -0.05
    ä½ľ
    -0.05
    çĶļ
    -0.05
    æĿ¥åĪ°
    -0.05
    astes
    -0.05
    亲çĪ±çļĦ
    -0.05
    POSITIVE LOGITS
    åĪĿå§ĭ
    0.10
    -initial
    0.10
     initial
    0.09
     initially
    0.09
    Initial
    0.09
    Initially
    0.09
     Initially
    0.09
     Initial
    0.09
    initial
    0.09
    èµ·åĪĿ
    0.09
    Activations Density 0.167%

    No Known Activations