© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 68754
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
     temperatura
    -0.08
     soil
    -0.07
     vanish
    -0.07
    .setRotation
    -0.07
     territor
    -0.07
    villa
    -0.07
    ADER
    -0.06
    san
    -0.06
     vad
    -0.06
     Ships
    -0.06
    POSITIVE LOGITS
     quản
    0.07
    FIELD
    0.07
    ক
    0.06
    哽
    0.06
     되
    0.06
    平行
    0.06
    Option
    0.06
    Collapse
    0.06
     Currency
    0.06
     beginnings
    0.06
    Activations Density 0.041%

    No Known Activations