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. 44042
    Prev
    Next
    INDEX
    Explanations

    medical, pharmaceutical texts, drugs

    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
     grit
    -0.07
    啮
    -0.07
     acqu
    -0.07
     '/',↵
    -0.07
     eagerly
    -0.07
    文物
    -0.07
    𝓊
    -0.06
    oncé
    -0.06
    罔
    -0.06
    干涉
    -0.06
    POSITIVE LOGITS
    领军
    0.07
    AdapterManager
    0.07
    ,NULL
    0.07
    トップ
    0.06
     Publié
    0.06
    ombs
    0.06
    ἶ
    0.06
     다음과
    0.06
    为你
    0.06
    <span
    0.06
    Activations Density 0.148%

    No Known Activations