© 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. 15-RESID-POST-AA
    6. 128278
    Prev
    Next
    INDEX
    Explanations

    =

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [('
    -0.07
     complaining
    -0.07
    .getRandom
    -0.07
    -gun
    -0.07
     maxx
    -0.06
     dispar
    -0.06
     Jerseys
    -0.06
    迫不及待
    -0.06
     bons
    -0.06
     complains
    -0.06
    POSITIVE LOGITS
     سيتم
    0.08
    calendar
    0.07
     personally
    0.07
     tương
    0.07
    ウォー
    0.07
    ermo
    0.07
    -c
    0.07
     ideology
    0.07
    flux
    0.07
    🏿
    0.07
    Activations Density 0.018%

    No Known Activations