© 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 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. 15-RESID-POST-AA
    11. 53648
    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
    (cuda
    -0.08
    (gulp
    -0.07
    赶上
    -0.07
    quotes
    -0.07
    袢
    -0.07
    .getPort
    -0.07
     refute
    -0.07
    becue
    -0.07
    .cgi
    -0.07
     Cons
    -0.07
    POSITIVE LOGITS
    Clear
    0.07
    Ta
    0.07
    ţ
    0.07
    Fixed
    0.07
    =key
    0.07
    льц
    0.07
     Scal
    0.07
    Repair
    0.06
     play
    0.06
     rendre
    0.06
    Activations Density 0.001%

    No Known Activations