© 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. 73391
    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
    我说
    -0.08
    -offs
    -0.07
    urette
    -0.07
    走出去
    -0.07
    ournaments
    -0.06
    azz
    -0.06
    تخط
    -0.06
     Outside
    -0.06
    нич
    -0.06
    	out
    -0.06
    POSITIVE LOGITS
     Temporary
    0.08
    כנו
    0.08
    processing
    0.07
     Registration
    0.07
    Chunks
    0.07
    _nm
    0.07
    cpf
    0.07
    /repos
    0.07
     Aad
    0.07
     gly
    0.07
    Activations Density 0.008%

    No Known Activations