Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 10785
    Prev
    Next
    INDEX
    Explanations

    operating systems

    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
    ollision
    -0.07
     Penal
    -0.07
     Cảnh
    -0.07
    폴
    -0.07
    虹
    -0.07
    _APP
    -0.07
     This
    -0.06
    _AUTO
    -0.06
     CV
    -0.06
     Rune
    -0.06
    POSITIVE LOGITS
    Titulo
    0.08
    $current
    0.08
    控股股东
    0.08
    ToSelector
    0.08
     ATI
    0.07
    рабатыва
    0.07
     agenda
    0.07
    大咖
    0.07
     quello
    0.07
    qid
    0.07
    Activations Density 0.032%

    No Known Activations