© 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. 81823
    Prev
    Next
    INDEX
    Explanations

    institutions and businesses

    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
     modelo
    -0.08
    OPTARG
    -0.07
     Connectivity
    -0.07
     מכל
    -0.07
    ('//*[@
    -0.07
    JPEG
    -0.07
    ibold
    -0.07
    \model
    -0.07
    (strtolower
    -0.07
     knowledge
    -0.07
    POSITIVE LOGITS
    واقع
    0.07
    单位
    0.07
    学者
    0.07
     Psi
    0.07
    נית
    0.07
    欲
    0.07
    ads
    0.06
    胃
    0.06
    翼
    0.06
    人际
    0.06
    Activations Density 0.251%

    No Known Activations