© 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. 28499
    Prev
    Next
    INDEX
    Explanations

    glasses

    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
     يؤدي
    -0.09
     '((
    -0.08
    (and
    -0.07
    ieved
    -0.07
    {|
    -0.07
    uell
    -0.07
    idents
    -0.07
    reward
    -0.07
     Increases
    -0.07
    .Txt
    -0.07
    POSITIVE LOGITS
    �
    0.07
    _PIXEL
    0.07
     בכ
    0.07
    �
    0.07
    =dict
    0.07
    底盘
    0.07
    ァ
    0.07
    PARAM
    0.07
    쌘
    0.07
    🥣
    0.07
    Activations Density 0.005%

    No Known Activations