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. 59618
    Prev
    Next
    INDEX
    Explanations

    left

    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
    体育
    -0.07
    堆
    -0.07
    IDEO
    -0.07
    Õ
    -0.07
     như
    -0.07
    弥漫
    -0.06
    بو
    -0.06
    icion
    -0.06
    recogn
    -0.06
     öğrenc
    -0.06
    POSITIVE LOGITS
     Variant
    0.07
     Highest
    0.07
     DataRow
    0.07
    큠
    0.06
     "//
    0.06
     ajout
    0.06
     accurate
    0.06
    ��
    0.06
     preca
    0.06
     зая
    0.06
    Activations Density 0.004%

    No Known Activations