© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 81960
    Prev
    Next
    INDEX
    Explanations

    aromatic

    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
     Huck
    -0.07
     Outline
    -0.07
     textbook
    -0.07
    .flat
    -0.07
    werk
    -0.07
    	fill
    -0.07
    祖父
    -0.07
     Enrique
    -0.07
    yll
    -0.07
     espacio
    -0.07
    POSITIVE LOGITS
    �
    0.07
    تحر
    0.07
    .compile
    0.07
     aesthetic
    0.07
    здоров
    0.07
    bestos
    0.07
     yetiştir
    0.06
    ábado
    0.06
     cats
    0.06
     wearing
    0.06
    Activations Density 0.006%

    No Known Activations