© 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. 19-RESID-POST-AA
    11. 8001
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     after
    -0.07
    算
    -0.07
     иностранн
    -0.07
    莸
    -0.06
    就知道
    -0.06
     syn
    -0.06
    สงคร
    -0.06
     קנ
    -0.06
     artır
    -0.06
     buddy
    -0.06
    POSITIVE LOGITS
    bach
    0.07
     Columbia
    0.07
    杭州
    0.07
     Rockefeller
    0.07
     época
    0.07
    二级
    0.06
     entrepreneurs
    0.06
     cybersecurity
    0.06
     karma
    0.06
     Mandela
    0.06
    Activations Density 0.039%

    No Known Activations