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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 48924
    Prev
    Next
    INDEX
    Explanations

    temporal

    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
     newbie
    -0.08
    仨
    -0.08
    梅
    -0.08
    -transition
    -0.07
    Blueprint
    -0.07
     Sor
    -0.07
    🌄
    -0.07
     backpage
    -0.07
    مرحلة
    -0.07
    แสด
    -0.07
    POSITIVE LOGITS
    iazza
    0.08
    currency
    0.07
    变换
    0.06
    ディ
    0.06
     fixed
    0.06
     regions
    0.06
     نقط
    0.06
    支配
    0.06
    .wait
    0.06
    eded
    0.06
    Activations Density 0.004%

    No Known Activations