© 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. 45861
    Prev
    Next
    INDEX
    Explanations

    Parentheses and dashes

    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
     posicion
    -0.07
    之前
    -0.07
    -function
    -0.07
    ample
    -0.07
     sexdate
    -0.06
     Mahar
    -0.06
    MBOL
    -0.06
    range
    -0.06
    免责
    -0.06
     strife
    -0.06
    POSITIVE LOGITS
    ductor
    0.07
     pendant
    0.07
    滅
    0.07
    诱导
    0.06
    偻
    0.06
     около
    0.06
    .endTime
    0.06
    ⌣
    0.06
     zero
    0.06
    ⎾
    0.06
    Activations Density 0.029%

    No Known Activations