© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 19-RESID-POST-AA
    11. 8390
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    もちろ
    -0.07
     visible
    -0.07
    Christopher
    -0.07
    usi
    -0.07
    thy
    -0.06
    /lists
    -0.06
    .Nil
    -0.06
    _por
    -0.06
     tuberculosis
    -0.06
    植树
    -0.06
    POSITIVE LOGITS
     Walk
    0.08
     hydration
    0.07
     magnet
    0.07
     áll
    0.07
    邦
    0.07
     Strap
    0.07
    =Math
    0.07
     lässt
    0.07
     badge
    0.07
    CONNECT
    0.06
    Activations Density 0.032%

    No Known Activations