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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 76742
    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
    .selected
    -0.08
    也被
    -0.07
     regul
    -0.07
     ngày
    -0.06
     даж
    -0.06
     systematically
    -0.06
    合适
    -0.06
     Xxx
    -0.06
    ühr
    -0.06
     heritage
    -0.06
    POSITIVE LOGITS
     وذلك
    0.08
    redential
    0.08
    ⇵
    0.07
    _axes
    0.07
    0.07
    🥧
    0.07
    leen
    0.07
    at
    0.07
    ARK
    0.07
     yaw
    0.07
    Activations Density 0.002%

    No Known Activations