© 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. 79077
    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
     memorandum
    -0.08
    发布了
    -0.07
    	Use
    -0.07
    北汽
    -0.06
     października
    -0.06
    Ὃ
    -0.06
    沨
    -0.06
     Fiji
    -0.06
    お金を
    -0.06
     fright
    -0.06
    POSITIVE LOGITS
     ---↵
    0.07
    ولوجي
    0.07
     COR
    0.07
     Colbert
    0.07
     residents
    0.07
    loads
    0.07
    hood
    0.07
    确诊病例
    0.07
    CD
    0.07
     Ket
    0.07
    Activations Density 3.150%

    No Known Activations