© 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. 126121
    Prev
    Next
    INDEX
    Explanations

    on

    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
     via
    -0.07
     Thành
    -0.07
    嘴巴
    -0.07
    巨
    -0.06
     مع
    -0.06
     jednocze
    -0.06
    新农村
    -0.06
    Ự
    -0.06
    쩝
    -0.06
    下巴
    -0.06
    POSITIVE LOGITS
    #g
    0.07
    plorer
    0.07
    人たち
    0.07
     theaters
    0.07
    봇
    0.07
    eturn
    0.07
    🍆
    0.07
     apex
    0.07
     hive
    0.07
    )e
    0.07
    Activations Density 0.006%

    No Known Activations