© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 77214
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﯓ
    -0.08
    ﯞ
    -0.08
     عبدالله
    -0.08
     programas
    -0.07
    autorelease
    -0.07
    亸
    -0.07
    ན
    -0.07
     Emotional
    -0.07
    IPH
    -0.07
     البريطاني
    -0.07
    POSITIVE LOGITS
    	edit
    0.07
     mActivity
    0.07
    entimes
    0.07
     Already
    0.07
    ()*
    0.07
    \Collections
    0.07
    感觉
    0.07
     ticking
    0.07
    Okay
    0.07
    .double
    0.07
    Activations Density 0.000%

    No Known Activations