© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 86304
    Prev
    Next
    INDEX
    Explanations

    6

    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
    雁
    -0.07
    擞
    -0.07
    azers
    -0.07
    俾
    -0.07
     simply
    -0.07
    步骤
    -0.06
    𬭳
    -0.06
    鲍
    -0.06
     gee
    -0.06
    ANG
    -0.06
    POSITIVE LOGITS
     Detection
    0.07
     turtle
    0.07
    Client
    0.07
    ]&
    0.07
    Digital
    0.07
    >An
    0.07
     Papers
    0.07
    ']==
    0.07
    .setInput
    0.07
     instrument
    0.07
    Activations Density 0.001%

    No Known Activations