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

    Neuronpedia

    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. 77642
    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
    [item
    -0.07
     viewPager
    -0.07
    .PropTypes
    -0.07
    (UINT
    -0.07
    捆
    -0.07
    BackgroundColor
    -0.07
    [prop
    -0.07
     striped
    -0.07
     polym
    -0.07
     pesticide
    -0.07
    POSITIVE LOGITS
    .star
    0.08
     société
    0.07
                                   ↵
    0.07
     llegar
    0.07
    .")
↵
    0.07
     promotions
    0.07
     Lac
    0.07
    :")↵
    0.07
    rão
    0.07
    社會
    0.06
    Activations Density 0.002%

    No Known Activations