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. 15-RESID-POST-AA
    6. 120695
    Prev
    Next
    INDEX
    Explanations

    The number 2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -cut
    -0.07
    紧凑
    -0.07
     q
    -0.07
     pinpoint
    -0.06
    巡
    -0.06
    弹
    -0.06
    莸
    -0.06
     sponsor
    -0.06
    适应
    -0.06
     sta
    -0.06
    POSITIVE LOGITS
    מיקום
    0.07
     obliged
    0.07
    .labels
    0.07
    散发着
    0.07
    ивается
    0.07
     항상
    0.06
    .Office
    0.06
     StyleSheet
    0.06
    ificado
    0.06
     всегда
    0.06
    Activations Density 0.005%

    No Known Activations