© 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. 11-RESID-POST-AA
    6. 2757
    Prev
    Next
    INDEX
    Explanations

    hydrophobicity

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     إدارة
    -0.07
    pets
    -0.07
    '}).
    -0.07
    �
    -0.07
    /date
    -0.07
    .MouseEvent
    -0.07
    )./
    -0.07
     tố
    -0.07
     arquivo
    -0.06
    озв
    -0.06
    POSITIVE LOGITS
     берем
    0.07
    Would
    0.07
    StringUtil
    0.07
    Bot
    0.06
     propri
    0.06
    pret
    0.06
    (dynamic
    0.06
     Applies
    0.06
    プ
    0.06
    сим
    0.06
    Activations Density 0.052%

    No Known Activations