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. 24653
    Prev
    Next
    INDEX
    Explanations

    spit

    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
    躺在
    -0.07
     velvet
    -0.07
     prepaid
    -0.06
    响起
    -0.06
     paddle
    -0.06
    谕
    -0.06
    以人为
    -0.06
    撑
    -0.06
    绿色
    -0.06
    вен
    -0.06
    POSITIVE LOGITS
    ﻃ
    0.07
    Bg
    0.07
    íf
    0.07
     ICU
    0.07
    fp
    0.07
    对照检查
    0.06
    סביר
    0.06
    serter
    0.06
    enticator
    0.06
    提供商
    0.06
    Activations Density 0.005%

    No Known Activations