© 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. 42094
    Prev
    Next
    INDEX
    Explanations

    arguments

    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
    GT
    -0.08
    闿
    -0.07
     Lap
    -0.07
     dot
    -0.07
    气势
    -0.07
    温暖
    -0.06
     gad
    -0.06
     Administr
    -0.06
     escape
    -0.06
     gay
    -0.06
    POSITIVE LOGITS
    orestation
    0.08
    .metrics
    0.08
    ่วย
    0.08
    .micro
    0.07
    Fixture
    0.07
    ernet
    0.07
    فرق
    0.07
     Belize
    0.07
    מעות
    0.07
    📡
    0.07
    Activations Density 0.009%

    No Known Activations