© 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. 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. 64604
    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
    rough
    -0.08
     rooftop
    -0.07
    .java
    -0.07
     Granted
    -0.07
    ibrary
    -0.07
     lacked
    -0.07
     Basics
    -0.06
    ностей
    -0.06
     Bills
    -0.06
    bf
    -0.06
    POSITIVE LOGITS
    .easing
    0.07
    ##↵↵
    0.07
     #↵
    0.07
     rects
    0.07
    	Intent
    0.07
     #↵↵
    0.07
     Stuart
    0.07
    	from
    0.07
    ///↵↵
    0.07
    läss
    0.06
    Activations Density 0.046%

    No Known Activations