© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 23647
    Prev
    Next
    INDEX
    Explanations

    probability with letters

    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
    enting
    -0.07
    感冒
    -0.07
    diğ
    -0.07
    戭
    -0.06
    kerja
    -0.06
     dú
    -0.06
    ▯
    -0.06
    ձ
    -0.06
     drill
    -0.06
     reliant
    -0.06
    POSITIVE LOGITS
     Boots
    0.09
     Auschwitz
    0.08
     Thought
    0.08
     mortar
    0.07
     activations
    0.07
    鎏
    0.07
     المختلفة
    0.07
    Alloc
    0.07
     כתובת
    0.07
     onwards
    0.07
    Activations Density 0.006%

    No Known Activations