Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 35726
    Prev
    Next
    INDEX
    Explanations

    recommendation

    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
    resume
    -0.08
     Admiral
    -0.08
    xBB
    -0.07
    Test
    -0.07
    agree
    -0.07
     certs
    -0.07
    Pdf
    -0.06
     Rest
    -0.06
     gu
    -0.06
     establishment
    -0.06
    POSITIVE LOGITS
    一片
    0.08
    ↫
    0.07
     motivations
    0.07
    徜
    0.07
    公开发
    0.07
     distancing
    0.07
     krat
    0.07
    .localScale
    0.07
     האלה
    0.07
     Zot
    0.07
    Activations Density 0.015%

    No Known Activations