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

    Neuronpedia

    APICircuit 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. 2499
    Prev
    Next
    INDEX
    Explanations

    to

    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
    معرف
    -0.08
    لاح
    -0.07
    .tpl
    -0.07
    -decoration
    -0.07
     irrigation
    -0.07
    树枝
    -0.07
    ﰒ
    -0.07
    بوابة
    -0.07
     untouched
    -0.07
    臑
    -0.07
    POSITIVE LOGITS
    /navbar
    0.08
    结局
    0.07
    VRTX
    0.07
     essential
    0.07
     mpg
    0.07
    _questions
    0.07
    %(
    0.07
     subst
    0.07
    ведущ
    0.07
     öğrenciler
    0.07
    Activations Density 0.006%

    No Known Activations