© 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. 13190
    Prev
    Next
    INDEX
    Explanations

    code creation

    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
     submitting
    -0.08
    Winter
    -0.07
    own
    -0.07
    茨
    -0.07
     software
    -0.07
    outines
    -0.07
    对公司
    -0.07
     homes
    -0.07
    (rng
    -0.07
     freshwater
    -0.06
    POSITIVE LOGITS
    ᵏ
    0.07
    )p
    0.07
    )sender
    0.06
    歐
    0.06
     THERE
    0.06
    equal
    0.06
    ]string
    0.06
    两千
    0.06
    междуна
    0.06
    Thirty
    0.06
    Activations Density 0.107%

    No Known Activations