© 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. 7-RESID-POST-AA
    11. 40981
    Prev
    Next
    INDEX
    Explanations

    Web browsing and accessibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ()/
    -0.07
     thắng
    -0.07
    并在
    -0.07
     insults
    -0.06
    尤其是
    -0.06
    ENTA
    -0.06
    将是
    -0.06
    一脸
    -0.06
     hầu
    -0.06
    汉子
    -0.06
    POSITIVE LOGITS
    yon
    0.07
     Aph
    0.07
    (prog
    0.07
     Scor
    0.07
     Tibetan
    0.07
    载
    0.07
      
    0.07
     Preconditions
    0.06
    qualified
    0.06
    (@"%@",
    0.06
    Activations Density 0.228%

    No Known Activations