© 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. 60789
    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
    装备制造
    -0.07
    �
    -0.07
     thậm
    -0.07
    (entry
    -0.07
    ampions
    -0.07
    ({...
    -0.07
    stripe
    -0.07
    基调
    -0.07
    jon
    -0.07
    撞击
    -0.07
    POSITIVE LOGITS
     practical
    0.08
    \">"
    0.07
    ourg
    0.07
    乎
    0.07
     glEnable
    0.07
     \
    0.07
     accumulated
    0.07
    뻔
    0.07
    ](
    0.06
    형
    0.06
    Activations Density 0.014%

    No Known Activations