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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 39610
    Prev
    Next
    INDEX
    Explanations

    destabil

    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
     liaison
    -0.07
    (rp
    -0.07
     iw
    -0.07
    api
    -0.07
     recorded
    -0.07
     neutr
    -0.07
    (nextProps
    -0.07
     op
    -0.07
    Line
    -0.06
     eos
    -0.06
    POSITIVE LOGITS
     deliberate
    0.08
    PixelFormat
    0.07
     Shelby
    0.07
    سياسات
    0.07
    .SqlClient
    0.07
    שמחה
    0.07
     استراتيجية
    0.07
    淡淡的
    0.07
     Dennis
    0.07
     Stud
    0.07
    Activations Density 0.006%

    No Known Activations