© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 70177
    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
    Negative Logits
    𬬸
    -0.07
    �
    -0.06
    $stmt
    -0.06
    𝐟
    -0.06
     норм
    -0.06
    אמא
    -0.06
    structured
    -0.06
    ]
↵
↵
    -0.06
     от
    -0.06
     Cardio
    -0.06
    POSITIVE LOGITS
    (Gravity
    0.07
    四种
    0.07
    leet
    0.07
    È
    0.07
    一點
    0.07
    正是
    0.07
     magically
    0.07
     draggable
    0.07
     rushes
    0.06
     sixteen
    0.06
    Activations Density 0.793%

    No Known Activations