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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RESID-POST-AA
    11. 81980
    Prev
    Next
    INDEX
    Explanations

    Name Julien

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     amet
    -0.07
    ϶
    -0.07
    ሐ
    -0.07
    Ḩ
    -0.07
    PLIER
    -0.07
     eh
    -0.07
    -bootstrap
    -0.06
    /backend
    -0.06
    .copyWith
    -0.06
     BASE
    -0.06
    POSITIVE LOGITS
     scripting
    0.09
    阐明
    0.08
     Providence
    0.08
    标志着
    0.07
    ][:
    0.07
    -world
    0.07
    无疑
    0.07
    jen
    0.07
    淋
    0.07
     violating
    0.07
    Activations Density 0.001%

    No Known Activations