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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RESID-POST-AA
    11. 2827
    Prev
    Next
    INDEX
    Explanations

    lifetime average calculation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     attendee
    -0.08
    sensor
    -0.08
    AGAIN
    -0.07
     inducing
    -0.07
    なくても
    -0.07
    بال
    -0.07
     SPEED
    -0.07
    悪
    -0.07
    (person
    -0.07
     abdomen
    -0.07
    POSITIVE LOGITS
    𝘨
    0.08
    九
    0.08
    人们对
    0.07
     образом
    0.06
    घ
    0.06
    第一条
    0.06
    _conf
    0.06
    igail
    0.06
    配套
    0.06
    ught
    0.06
    Activations Density 0.068%

    No Known Activations