© 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. 19-RESID-POST-AA
    11. 89489
    Prev
    Next
    INDEX
    Explanations

    Code configuration files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    풂
    -0.07
    Stopped
    -0.07
    Carousel
    -0.07
    gesch
    -0.07
    -generic
    -0.07
    跟不上
    -0.07
    .unsubscribe
    -0.07
    結束
    -0.07
    mith
    -0.07
    -tooltip
    -0.06
    POSITIVE LOGITS
     LOCATION
    0.07
     largely
    0.06
    سائر
    0.06
     numer
    0.06
     YA
    0.06
    📴
    0.06
    ANA
    0.06
     planetary
    0.06
    iang
    0.06
     البن
    0.06
    Activations Density 0.007%

    No Known Activations