© 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. 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. 74736
    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
    de
    -0.07
    زهر
    -0.07
     decorators
    -0.06
     #-}↵
    -0.06
    near
    -0.06
    	arg
    -0.06
     }}>
    -0.06
     Nullable
    -0.06
     Legislature
    -0.06
    代言
    -0.06
    POSITIVE LOGITS
    ċ
    0.08
    .Ref
    0.07
    EndTime
    0.07
    出院
    0.07
     chained
    0.07
    	Main
    0.06
    根源
    0.06
     pest
    0.06
     closing
    0.06
    (gcf
    0.06
    Activations Density 0.042%

    No Known Activations