© 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. 128826
    Prev
    Next
    INDEX
    Explanations

    laparoscopy

    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
     xây
    -0.08
    ﭓ
    -0.07
    (pDX
    -0.07
    _gshared
    -0.07
    .openConnection
    -0.07
    Ӣ
    -0.07
    🕑
    -0.07
     Tunisia
    -0.07
    超强
    -0.07
    鲧
    -0.07
    POSITIVE LOGITS
    ער
    0.07
    的需求
    0.07
    heritance
    0.07
    的想法
    0.07
    POS
    0.07
     cortex
    0.07
    uchen
    0.07
    Marcus
    0.07
     Graves
    0.07
    低い
    0.07
    Activations Density 0.010%

    No Known Activations