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. 31322
    Prev
    Next
    INDEX
    Explanations

    non-English text

    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
     Sox
    -0.07
    верх
    -0.07
     더욱
    -0.07
    芡
    -0.06
     testified
    -0.06
     Attorney
    -0.06
     Amend
    -0.06
    钛
    -0.06
     editions
    -0.06
     Tiến
    -0.06
    POSITIVE LOGITS
    延长
    0.07
    Parsing
    0.07
    她是
    0.07
     Wag
    0.07
     profile
    0.07
    冲洗
    0.07
    (listener
    0.06
    -article
    0.06
     pole
    0.06
    ")]
    0.06
    Activations Density 0.097%

    No Known Activations