© 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. 76133
    Prev
    Next
    INDEX
    Explanations

    2

    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
    childs
    -0.07
     Home
    -0.07
    Education
    -0.07
     sos
    -0.07
    basic
    -0.07
    也要
    -0.07
     requestData
    -0.07
    прос
    -0.07
    趣
    -0.07
    gregate
    -0.07
    POSITIVE LOGITS
    _PREVIEW
    0.07
    ⚟
    0.07
     shower
    0.06
    席执行官
    0.06
     Eag
    0.06
    娩
    0.06
    公元前
    0.06
    LoginPage
    0.06
    痂
    0.06
     drum
    0.06
    Activations Density 0.000%

    No Known Activations