© 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
    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. 3160
    Prev
    Next
    INDEX
    Explanations

    Math and 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
    gaben
    -0.08
    kaar
    -0.08
    쇤
    -0.07
    -append
    -0.07
    twór
    -0.07
     quảng
    -0.07
    허
    -0.07
    뒬
    -0.07
    𝕚
    -0.07
    怩
    -0.07
    POSITIVE LOGITS
    时期
    0.07
     Ac
    0.07
    structural
    0.07
     System
    0.07
     Material
    0.07
    (map
    0.07
     Arte
    0.07
     Macy
    0.06
    parser
    0.06
    阶层
    0.06
    Activations Density 0.032%

    No Known Activations