© 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. 109478
    Prev
    Next
    INDEX
    Explanations

    Indianapolis

    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
    Messaging
    -0.08
    summ
    -0.07
    ߢ
    -0.07
    吸引
    -0.07
     ed
    -0.07
    Den
    -0.07
    .j
    -0.07
    假
    -0.06
    CM
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    į
    0.07
     advisable
    0.07
     Equipment
    0.07
    けれ
    0.07
     Above
    0.06
    试图
    0.06
     бол
    0.06
    ateg
    0.06
     выпол
    0.06
    Const
    0.06
    Activations Density 0.039%

    No Known Activations