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. 2355
    Prev
    Next
    INDEX
    Explanations

    Kinases/proteins (ATM, SYK)

    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
     ממש
    -0.07
    🐜
    -0.07
    .BadRequest
    -0.07
    UIViewController
    -0.07
    useppe
    -0.07
    ddd
    -0.07
    Employ
    -0.07
     рань
    -0.07
     Gebäude
    -0.07
    eldom
    -0.07
    POSITIVE LOGITS
    浏
    0.07
     revealed
    0.07
    Slots
    0.07
    Cou
    0.07
     alignments
    0.07
    但仍
    0.06
     mult
    0.06
     evolves
    0.06
    꿋
    0.06
    "]==
    0.06
    Activations Density 0.009%

    No Known Activations