© 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. 23-RESID-POST-AA
    6. 1129
    Prev
    Next
    INDEX
    Explanations

    register

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     чуть
    -0.07
    ทำความ
    -0.07
    午
    -0.07
    _MAY
    -0.07
    凓
    -0.07
     Par
    -0.07
     house
    -0.06
    เอ
    -0.06
    你怎么
    -0.06
    ngo
    -0.06
    POSITIVE LOGITS
    -driver
    0.08
    _inventory
    0.08
     includ
    0.08
     Binding
    0.07
     analyses
    0.07
    schüt
    0.07
     manipulation
    0.07
    --,
    0.07
    ))/(
    0.07
    崶
    0.07
    Activations Density 0.002%

    No Known Activations