© 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. 30490
    Prev
    Next
    INDEX
    Explanations

    Mixed, technical content

    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
    ARG
    -0.07
    _q
    -0.06
     apart
    -0.06
     It
    -0.06
     Estados
    -0.06
    hs
    -0.06
    ape
    -0.06
     stellen
    -0.06
    ecture
    -0.06
    不同意
    -0.06
    POSITIVE LOGITS
     migr
    0.08
    _TRACE
    0.08
    (pDX
    0.07
    招聘
    0.07
    (width
    0.07
    年起
    0.07
     louis
    0.07
     المتوسط
    0.07
     Consulting
    0.07
     slang
    0.07
    Activations Density 0.028%

    No Known Activations