© 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. 21718
    Prev
    Next
    INDEX
    Explanations

    **alarmist or exaggerated claims**

    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
    ìĦľëĬĶ
    -0.05
    åĩłæ¬¾
    -0.05
    è´¢
    -0.05
     Puzz
    -0.05
    iq
    -0.05
    ihin
    -0.05
    plex
    -0.05
    bind
    -0.05
    å±ĢéĿ¢
    -0.05
    si
    -0.05
    POSITIVE LOGITS
     exagger
    0.10
    å¤¸å¼ł
    0.09
     exaggerated
    0.09
    夸大
    0.08
    èªĩå¼µ
    0.07
     exager
    0.07
     overst
    0.07
    çĻ¾åĢį
    0.07
    åĪ°æŀģèĩ´
    0.07
    åĢįæķ°
    0.07
    Activations Density 0.013%

    No Known Activations