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. 19-RESID-POST-AA
    6. 131063
    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_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
    udev
    -0.07
     divisions
    -0.06
    ("-");↵
    -0.06
     бон
    -0.06
     xd
    -0.06
     рест
    -0.06
    DOMNode
    -0.06
     dbName
    -0.06
    	iNdEx
    -0.06
    itory
    -0.06
    POSITIVE LOGITS
    תשובה
    0.08
     Example
    0.08
    ee
    0.08
     remarks
    0.07
    exterity
    0.07
    _Entry
    0.07
    ☍
    0.07
    تي
    0.07
    _handle
    0.07
     meas
    0.07
    Activations Density 0.008%

    No Known Activations