Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 56296
    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
    )"
    -0.07
    тал
    -0.07
     riding
    -0.06
     abund
    -0.06
     finally
    -0.06
    ?"
    -0.06
    )،
    -0.06
    kt
    -0.06
     Dan
    -0.06
    ..↵
    -0.06
    POSITIVE LOGITS
    ⚣
    0.08
    éro
    0.07
    nga
    0.07
    .Transform
    0.07
    .ship
    0.07
    olucion
    0.07
    (div
    0.07
     Sting
    0.07
    орт
    0.07
    𣗋
    0.06
    Activations Density 0.055%

    No Known Activations