© 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. 15-RESID-POST-AA
    11. 4288
    Prev
    Next
    INDEX
    Explanations

    I-beams and structures

    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_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
     Defense
    -0.07
    .ur
    -0.07
    舍
    -0.07
     loadChildren
    -0.06
    讓他們
    -0.06
     presum
    -0.06
    シア
    -0.06
    앺
    -0.06
     precondition
    -0.06
    organizations
    -0.06
    POSITIVE LOGITS
    蠊
    0.08
    深刻的
    0.08
     Whale
    0.07
    ,model
    0.07
     Kernel
    0.07
    洛阳
    0.07
     Matthias
    0.07
    iben
    0.07
    ⊥
    0.07
     Matt
    0.07
    Activations Density 0.010%

    No Known Activations