© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 24576
    Prev
    Next
    INDEX
    Explanations

    stir

    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
     ה
    -0.07
    肺
    -0.07
    telefono
    -0.07
     của
    -0.07
    inel
    -0.07
    婚姻
    -0.07
    @↵
    -0.07
     sexually
    -0.07
    这个职业
    -0.07
    альное
    -0.07
    POSITIVE LOGITS
     сбор
    0.08
    .Function
    0.07
     Argument
    0.07
    按摩
    0.07
     กร
    0.07
     aggrav
    0.07
     stir
    0.07
    诂
    0.07
     grabbing
    0.07
     지난
    0.06
    Activations Density 0.007%

    No Known Activations