© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 70788
    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
     Ler
    -0.07
                      ↵
    -0.07
    erti
    -0.07
     id
    -0.07
    告诉我
    -0.06
     ladies
    -0.06
                              ↵
    -0.06
    门户网站
    -0.06
     prompts
    -0.06
     upset
    -0.06
    POSITIVE LOGITS
    łę
    0.07
    etween
    0.07
     апр
    0.07
     sketches
    0.07
     fracking
    0.07
    耷
    0.07
    ämp
    0.07
     zale
    0.07
     massaggi
    0.07
     применя
    0.06
    Activations Density 0.099%

    No Known Activations