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. 87944
    Prev
    Next
    INDEX
    Explanations

    as

    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
     Interracial
    -0.08
    ermint
    -0.08
     lava
    -0.07
     mercado
    -0.07
    itung
    -0.07
    спект
    -0.07
    𝕴
    -0.07
     disple
    -0.07
     UITableViewDelegate
    -0.07
    ucene
    -0.07
    POSITIVE LOGITS
     associ
    0.07
     ARE
    0.07
    raised
    0.07
     bez
    0.07
    "In
    0.07
    ATA
    0.07
    ATORS
    0.07
     closed
    0.06
    .navigationController
    0.06
    KO
    0.06
    Activations Density 0.021%

    No Known Activations