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. 36438
    Prev
    Next
    INDEX
    Explanations

    group

    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
    Looking
    -0.07
    ⽼
    -0.07
    Ự
    -0.07
    ________________
    -0.06
    椆
    -0.06
    お願い
    -0.06
    😉
    -0.06
    两类
    -0.06
     setter
    -0.06
    POSITIVE LOGITS
    剪
    0.09
     Tiles
    0.07
     gala
    0.07
     balances
    0.07
    _repeat
    0.07
     Dag
    0.07
    olla
    0.07
     atte
    0.07
     palabra
    0.06
    ptions
    0.06
    Activations Density 0.043%

    No Known Activations