© 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. 7-RESID-POST-AA
    11. 39925
    Prev
    Next
    INDEX
    Explanations

    terror error

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    保
    -0.07
    가
    -0.07
    ASHINGTON
    -0.07
    厂家
    -0.07
     Indiana
    -0.07
    Devices
    -0.07
     Invitation
    -0.06
     erklä
    -0.06
    إل
    -0.06
    
    -0.06
    POSITIVE LOGITS
     Ronaldo
    0.08
     Terror
    0.07
    Screenshot
    0.07
    聘用
    0.07
    /uploads
    0.07
     usu
    0.07
     Wik
    0.07
    تصم
    0.07
    _sprites
    0.07
     abort
    0.07
    Activations Density 0.002%

    No Known Activations