Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 77890
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    uint
    -0.07
     tst
    -0.07
     coord
    -0.07
    Less
    -0.07
     accred
    -0.07
     Convenience
    -0.07
     crc
    -0.07
    คนไทย
    -0.07
     hầu
    -0.07
     utf
    -0.07
    POSITIVE LOGITS
    ;,
    0.07
    ENS
    0.06
    ]()
    0.06
    orianCalendar
    0.06
    ije
    0.06
    ά
    0.06
     choses
    0.06
    这件事
    0.06
    漪
    0.06
     touching
    0.06
    Activations Density 0.002%

    No Known Activations