Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 59469
    Prev
    Next
    INDEX
    Explanations

    oph

    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
    酆
    -0.07
     feud
    -0.07
    🦁
    -0.07
     CTRL
    -0.07
    报仇
    -0.07
    兕
    -0.06
     contentType
    -0.06
     محمد
    -0.06
     therap
    -0.06
    Qu
    -0.06
    POSITIVE LOGITS
    ᅮ
    0.07
    灾害
    0.07
    的经典
    0.07
     pumps
    0.07
     ולה
    0.06
    变压器
    0.06
    -specific
    0.06
    .ViewModels
    0.06
     pob
    0.06
    Hand
    0.06
    Activations Density 0.001%

    No Known Activations