© 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. 15-RESID-POST-AA
    11. 111564
    Prev
    Next
    INDEX
    Explanations

    Australia

    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_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
     easy
    -0.08
     dung
    -0.07
    变压器
    -0.07
     crosses
    -0.07
    /icon
    -0.07
     hiện
    -0.07
    Fr
    -0.07
    _WORK
    -0.07
     work
    -0.07
     mysqli
    -0.07
    POSITIVE LOGITS
    刹那
    0.08
    述べ
    0.07
    >(_
    0.07
     بدا
    0.07
     bv
    0.07
     outset
    0.07
    显然是
    0.07
     brand
    0.07
    บทความ
    0.07
     Shelf
    0.07
    Activations Density 0.019%

    No Known Activations