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. 87942
    Prev
    Next
    INDEX
    Explanations

    period

    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
    ➝
    -0.08
    ♗
    -0.07
    עבר
    -0.07
    ular
    -0.07
    elsif
    -0.07
     proceeds
    -0.07
    imary
    -0.07
    🌛
    -0.07
    �
    -0.06
    𝕏
    -0.06
    POSITIVE LOGITS
     đứa
    0.10
    .random
    0.08
    world
    0.08
     jou
    0.07
     hợ
    0.07
    .net
    0.07
     חול
    0.07
     glob
    0.07
    _pad
    0.07
    Intro
    0.07
    Activations Density 0.001%

    No Known Activations