© 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. 21126
    Prev
    Next
    INDEX
    Explanations

    parentheses

    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
     Hispanic
    -0.08
    的第一个
    -0.07
     >=
    -0.07
    (candidate
    -0.07
     impeccable
    -0.07
    (idx
    -0.07
     변경
    -0.07
     imminent
    -0.07
    [cur
    -0.07
     Tennessee
    -0.07
    POSITIVE LOGITS
     działalności
    0.07
    𝖘
    0.07
    🎿
    0.07
    stalk
    0.07
    罗斯
    0.07
    oomla
    0.07
    ـ
    0.06
    oodle
    0.06
    odium
    0.06
    oglobin
    0.06
    Activations Density 0.004%

    No Known Activations