© 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. 11-RESID-POST-AA
    11. 59831
    Prev
    Next
    INDEX
    Explanations

    formed

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _STEP
    -0.07
    ellen
    -0.07
    谨
    -0.07
    自救
    -0.07
     drawer
    -0.07
     factors
    -0.07
    动物园
    -0.07
     and
    -0.07
     fetchData
    -0.06
    停车
    -0.06
    POSITIVE LOGITS
    .sulake
    0.07
    -single
    0.07
    _news
    0.07
    _Stop
    0.07
    קים
    0.07
    _TIM
    0.06
    quer
    0.06
    :UIControlStateNormal
    0.06
    大众
    0.06
    third
    0.06
    Activations Density 0.013%

    No Known Activations