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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-RESID-POST-AA
    6. 7137
    Prev
    Next
    INDEX
    Explanations

    document fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ASTE
    -0.07
    ‶
    -0.07
     auprès
    -0.07
    Persons
    -0.07
    מצליח
    -0.07
     кажд
    -0.07
    を選
    -0.07
     conson
    -0.07
    隨著
    -0.07
     prayers
    -0.07
    POSITIVE LOGITS
     Zealand
    0.07
    Java
    0.07
    aint
    0.07
    _partner
    0.07
    ()][
    0.07
    化疗
    0.07
    .low
    0.06
    预测
    0.06
    负面影响
    0.06
    小白
    0.06
    Activations Density 0.003%

    No Known Activations