© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 6168
    Prev
    Next
    INDEX
    Explanations

    Server error logs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    工序
    -0.07
    伯
    -0.07
    哺乳
    -0.07
     frustration
    -0.06
     AHL
    -0.06
    �
    -0.06
    либо
    -0.06
    号楼
    -0.06
    を選ぶ
    -0.06
    .guid
    -0.06
    POSITIVE LOGITS
     Phật
    0.07
     Af
    0.07
    حداث
    0.07
     partido
    0.07
     brands
    0.07
    ‣
    0.07
     reduces
    0.07
    Г
    0.06
     pelos
    0.06
    Marca
    0.06
    Activations Density 0.036%

    No Known Activations