© 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. 19-RESID-POST-AA
    11. 76218
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
    新春
    -0.08
    彩色
    -0.08
     divul
    -0.08
     melhor
    -0.07
    辉煌
    -0.07
     propos
    -0.07
    专科
    -0.07
     cla
    -0.07
    最适合
    -0.07
     indiv
    -0.07
    POSITIVE LOGITS
     airstrikes
    0.08
    ?.
    0.07
    рез
    0.07
     Awake
    0.07
     cloud
    0.07
    transforms
    0.07
     زيادة
    0.07
    traits
    0.07
    BB
    0.07
     Abbott
    0.07
    Activations Density 0.014%

    No Known Activations