© 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. 20766
    Prev
    Next
    INDEX
    Explanations

    an

    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
    æ·¡
    -0.06
     باÙĦتÙĨ
    -0.06
    odge
    -0.06
    endencies
    -0.05
     Said
    -0.05
    andone
    -0.05
    )!=
    -0.05
    ÐľÐķÐĿ
    -0.05
    alternate
    -0.05
    ystate
    -0.05
    POSITIVE LOGITS
     stimuli
    0.07
    å§Ķå±Ī
    0.06
    obj
    0.06
    ÑĶ
    0.06
     triggers
    0.06
    åĪºæ¿Ģ
    0.05
    åIJİèĩ³
    0.05
    èĨ
    0.05
    çļĦåĪºæ¿Ģ
    0.05
    거리
    0.05
    Activations Density 0.022%

    No Known Activations