© 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. 19-RESID-POST-AA
    6. 76355
    Prev
    Next
    INDEX
    Explanations

    four

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     soaked
    -0.07
    マン
    -0.07
     diffusion
    -0.07
    几千
    -0.07
     disappointed
    -0.07
    _rsa
    -0.07
    щу
    -0.07
     nIndex
    -0.07
    泮
    -0.06
    畬
    -0.06
    POSITIVE LOGITS
    веч
    0.07
    랙
    0.07
     setVisible
    0.07
     successors
    0.07
    .Web
    0.07
    .ViewModel
    0.07
    (system
    0.06
    yclerView
    0.06
    ByEmail
    0.06
    早晨
    0.06
    Activations Density 0.209%

    No Known Activations