© 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. 23-RESID-POST-AA
    6. 1196
    Prev
    Next
    INDEX
    Explanations

    closures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ראית
    -0.07
    .school
    -0.07
    istrates
    -0.07
    믐
    -0.07
     freezes
    -0.07
     Estonia
    -0.07
     Debt
    -0.07
    ête
    -0.07
     extremists
    -0.06
    boom
    -0.06
    POSITIVE LOGITS
    "C
    0.07
     quint
    0.07
    销毁
    0.07
    を中心
    0.07
     QtCore
    0.07
    U
    0.07
    ('.
    0.07
    .mm
    0.06
    .DriverManager
    0.06
    spinner
    0.06
    Activations Density 0.039%

    No Known Activations