© 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. 77512
    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
     Chester
    -0.07
     pedal
    -0.07
    phony
    -0.07
     wyst
    -0.06
     todd
    -0.06
     }
↵
↵
    -0.06
    ಕ
    -0.06
     concurrent
    -0.06
     Mil
    -0.06
    uckles
    -0.06
    POSITIVE LOGITS
    _RT
    0.08
     ::↵
    0.07
    escription
    0.07
     triangle
    0.07
    (C
    0.07
     Explain
    0.07
    imization
    0.07
    模型
    0.07
     wants
    0.07
    接纳
    0.07
    Activations Density 0.104%

    No Known Activations